diff options
| author | Dimitry Andric <dim@FreeBSD.org> | 2010-09-17 15:48:55 +0000 |
|---|---|---|
| committer | Dimitry Andric <dim@FreeBSD.org> | 2010-09-17 15:48:55 +0000 |
| commit | d39c594d39df7f283c2fb8a704a3f31c501180d9 (patch) | |
| tree | 36453626c792cccd91f783a38a169d610a6b9db9 /test/CodeGen/ARM | |
| parent | 6144c1de6a7674dad94290650e4e14f24d42e421 (diff) | |
Notes
Diffstat (limited to 'test/CodeGen/ARM')
51 files changed, 1148 insertions, 601 deletions
diff --git a/test/CodeGen/ARM/2007-01-19-InfiniteLoop.ll b/test/CodeGen/ARM/2007-01-19-InfiniteLoop.ll index 81483cb4e7c55..ee63656b26d39 100644 --- a/test/CodeGen/ARM/2007-01-19-InfiniteLoop.ll +++ b/test/CodeGen/ARM/2007-01-19-InfiniteLoop.ll @@ -1,11 +1,15 @@ -; RUN: llc < %s -march=arm -mattr=+v6,+vfp2 +; RUN: llc < %s -march=arm -mattr=+v6,+vfp2 | FileCheck %s @quant_coef = external global [6 x [4 x [4 x i32]]] ; <[6 x [4 x [4 x i32]]]*> [#uses=1] @dequant_coef = external global [6 x [4 x [4 x i32]]] ; <[6 x [4 x [4 x i32]]]*> [#uses=1] @A = external global [4 x [4 x i32]] ; <[4 x [4 x i32]]*> [#uses=1] +; CHECK: dct_luma_sp: define fastcc i32 @dct_luma_sp(i32 %block_x, i32 %block_y, i32* %coeff_cost) { entry: +; Make sure to use base-updating stores for saving callee-saved registers. +; CHECK-NOT: sub sp +; CHECK: vstmdb sp! %predicted_block = alloca [4 x [4 x i32]], align 4 ; <[4 x [4 x i32]]*> [#uses=1] br label %cond_next489 diff --git a/test/CodeGen/ARM/2007-03-26-RegScavengerAssert.ll b/test/CodeGen/ARM/2007-03-26-RegScavengerAssert.ll index d741112e2886e..76fa3649c8806 100644 --- a/test/CodeGen/ARM/2007-03-26-RegScavengerAssert.ll +++ b/test/CodeGen/ARM/2007-03-26-RegScavengerAssert.ll @@ -2,7 +2,7 @@ ; PR1266 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64" -target triple = "arm-linux-gnueabi" +target triple = "arm-unknown-linux-gnueabi" %struct.CUMULATIVE_ARGS = type { i32, i32, i32, i32, i32, i32 } %struct.FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct.FILE*, i32, i32, i32, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i32, [52 x i8] } %struct.VEC_edge = type { i32, i32, [1 x %struct.edge_def*] } diff --git a/test/CodeGen/ARM/2007-05-31-RegScavengerInfiniteLoop.ll b/test/CodeGen/ARM/2007-05-31-RegScavengerInfiniteLoop.ll index 030486a7c9832..7ba2a190be734 100644 --- a/test/CodeGen/ARM/2007-05-31-RegScavengerInfiniteLoop.ll +++ b/test/CodeGen/ARM/2007-05-31-RegScavengerInfiniteLoop.ll @@ -2,7 +2,7 @@ ; PR1424 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64" -target triple = "arm-linux-gnueabi" +target triple = "arm-unknown-linux-gnueabi" %struct.AVClass = type { i8*, i8* (i8*)*, %struct.AVOption* } %struct.AVCodec = type { i8*, i32, i32, i32, i32 (%struct.AVCodecContext*)*, i32 (%struct.AVCodecContext*, i8*, i32, i8*)*, i32 (%struct.AVCodecContext*)*, i32 (%struct.AVCodecContext*, i8*, i32*, i8*, i32)*, i32, %struct.AVCodec*, void (%struct.AVCodecContext*)*, %struct.AVRational*, i32* } %struct.AVCodecContext = type { %struct.AVClass*, i32, i32, i32, i32, i32, i8*, i32, %struct.AVRational, i32, i32, i32, i32, i32, void (%struct.AVCodecContext*, %struct.AVFrame*, i32*, i32, i32, i32)*, i32, i32, i32, i32, i32, i32, i32, float, float, i32, i32, i32, i32, float, i32, i32, i32, %struct.AVCodec*, i8*, i32, i32, void (%struct.AVCodecContext*, i8*, i32, i32)*, i32, i32, i32, i32, i32, i32, i32, i32, i32, i8*, [32 x i8], i32, i32, i32, i32, i32, i32, i32, float, i32, i32 (%struct.AVCodecContext*, %struct.AVFrame*)*, void (%struct.AVCodecContext*, %struct.AVFrame*)*, i32, i32, i32, i32, i8*, i8*, float, float, i32, %struct.RcOverride*, i32, i8*, i32, i32, i32, float, float, float, float, i32, float, float, float, float, float, i32, i32, i32, i32*, i32, i32, i32, i32, %struct.AVRational, %struct.AVFrame*, i32, i32, [4 x i64], i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 (%struct.AVCodecContext*, i32*)*, i32, i32, i32, i32, i32, i32, i8*, i32, i32, i32, i32, i32, i32, i16*, i16*, i32, i32, i32, i32, %struct.AVPaletteControl*, i32, i32 (%struct.AVCodecContext*, %struct.AVFrame*)*, i32, i32, i32, i32, i32, i32, i32, i32 (%struct.AVCodecContext*, i32 (%struct.AVCodecContext*, i8*)*, i8**, i32*, i32)*, i8*, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, float, i32, i32, i32, i32, i32, i32, i32, i32, float, i32, i32, i32, i32, i32, i32, float, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i64 } diff --git a/test/CodeGen/ARM/2009-12-02-vtrn-undef.ll b/test/CodeGen/ARM/2009-12-02-vtrn-undef.ll index 198faebbea6f1..f89a5de77b3f5 100644 --- a/test/CodeGen/ARM/2009-12-02-vtrn-undef.ll +++ b/test/CodeGen/ARM/2009-12-02-vtrn-undef.ll @@ -17,3 +17,17 @@ entry: store <8 x i16> %1, <8 x i16>* %agg.result12.1.0, align 16 ret void } + +; Radar 8290937: Ignore undef shuffle indices. +; CHECK: t2 +; CHECK: vtrn.16 +define void @t2(%struct.int16x8x2_t* nocapture %ptr, <4 x i16> %a.0, <4 x i16> %b.0) nounwind { +entry: + %0 = shufflevector <4 x i16> %a.0, <4 x i16> undef, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 undef, i32 undef, i32 undef, i32 undef> + %1 = shufflevector <4 x i16> %a.0, <4 x i16> undef, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 undef, i32 undef, i32 undef, i32 undef> + %ptr26.0 = getelementptr inbounds %struct.int16x8x2_t* %ptr, i32 0, i32 0, i32 0, i32 0 + store <8 x i16> %0, <8 x i16>* %ptr26.0, align 16 + %ptr20.1.0 = getelementptr inbounds %struct.int16x8x2_t* %ptr, i32 0, i32 0, i32 1, i32 0 + store <8 x i16> %1, <8 x i16>* %ptr20.1.0, align 16 + ret void +} diff --git a/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll b/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll index ff60fa8c49d85..e47c038393754 100644 --- a/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll +++ b/test/CodeGen/ARM/2010-05-20-NEONSpillCrash.ll @@ -5,32 +5,32 @@ %struct.__neon_int8x8x3_t = type { <8 x i8>, <8 x i8>, <8 x i8> } -declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*) nounwind readonly +declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*, i32) nounwind readonly -declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind +declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind define <8 x i8> @t3(i8* %A1, i8* %A2, i8* %A3, i8* %A4, i8* %A5, i8* %A6, i8* %A7, i8* %A8, i8* %B) nounwind { - %tmp1b = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A2) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp1b = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A2, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=2] %tmp2b = extractvalue %struct.__neon_int8x8x3_t %tmp1b, 0 ; <<8 x i8>> [#uses=1] %tmp4b = extractvalue %struct.__neon_int8x8x3_t %tmp1b, 1 ; <<8 x i8>> [#uses=1] - %tmp1d = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A4) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp1d = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A4, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=2] %tmp2d = extractvalue %struct.__neon_int8x8x3_t %tmp1d, 0 ; <<8 x i8>> [#uses=1] %tmp4d = extractvalue %struct.__neon_int8x8x3_t %tmp1d, 1 ; <<8 x i8>> [#uses=1] - %tmp1e = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A5) ; <%struct.__neon_int8x8x3_t> [#uses=1] + %tmp1e = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A5, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=1] %tmp2e = extractvalue %struct.__neon_int8x8x3_t %tmp1e, 0 ; <<8 x i8>> [#uses=1] - %tmp1f = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A6) ; <%struct.__neon_int8x8x3_t> [#uses=1] + %tmp1f = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A6, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=1] %tmp2f = extractvalue %struct.__neon_int8x8x3_t %tmp1f, 0 ; <<8 x i8>> [#uses=1] - %tmp1g = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A7) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp1g = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A7, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=2] %tmp2g = extractvalue %struct.__neon_int8x8x3_t %tmp1g, 0 ; <<8 x i8>> [#uses=1] %tmp4g = extractvalue %struct.__neon_int8x8x3_t %tmp1g, 1 ; <<8 x i8>> [#uses=1] - %tmp1h = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A8) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp1h = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A8, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=2] %tmp2h = extractvalue %struct.__neon_int8x8x3_t %tmp1h, 0 ; <<8 x i8>> [#uses=1] %tmp3h = extractvalue %struct.__neon_int8x8x3_t %tmp1h, 2 ; <<8 x i8>> [#uses=1] %tmp2bd = add <8 x i8> %tmp2b, %tmp2d ; <<8 x i8>> [#uses=1] %tmp4bd = add <8 x i8> %tmp4b, %tmp4d ; <<8 x i8>> [#uses=1] %tmp2abcd = mul <8 x i8> undef, %tmp2bd ; <<8 x i8>> [#uses=1] %tmp4abcd = mul <8 x i8> undef, %tmp4bd ; <<8 x i8>> [#uses=2] - call void @llvm.arm.neon.vst3.v8i8(i8* %A1, <8 x i8> %tmp4abcd, <8 x i8> zeroinitializer, <8 x i8> %tmp2abcd) + call void @llvm.arm.neon.vst3.v8i8(i8* %A1, <8 x i8> %tmp4abcd, <8 x i8> zeroinitializer, <8 x i8> %tmp2abcd, i32 1) %tmp2ef = sub <8 x i8> %tmp2e, %tmp2f ; <<8 x i8>> [#uses=1] %tmp2gh = sub <8 x i8> %tmp2g, %tmp2h ; <<8 x i8>> [#uses=1] %tmp3gh = sub <8 x i8> zeroinitializer, %tmp3h ; <<8 x i8>> [#uses=1] @@ -38,8 +38,8 @@ define <8 x i8> @t3(i8* %A1, i8* %A2, i8* %A3, i8* %A4, i8* %A5, i8* %A6, i8* %A %tmp2efgh = mul <8 x i8> %tmp2ef, %tmp2gh ; <<8 x i8>> [#uses=1] %tmp3efgh = mul <8 x i8> undef, %tmp3gh ; <<8 x i8>> [#uses=1] %tmp4efgh = mul <8 x i8> %tmp4ef, undef ; <<8 x i8>> [#uses=2] - call void @llvm.arm.neon.vst3.v8i8(i8* %A2, <8 x i8> %tmp4efgh, <8 x i8> %tmp3efgh, <8 x i8> %tmp2efgh) + call void @llvm.arm.neon.vst3.v8i8(i8* %A2, <8 x i8> %tmp4efgh, <8 x i8> %tmp3efgh, <8 x i8> %tmp2efgh, i32 1) %tmp4 = sub <8 x i8> %tmp4efgh, %tmp4abcd ; <<8 x i8>> [#uses=1] - tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> zeroinitializer, <8 x i8> undef, <8 x i8> undef) + tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> zeroinitializer, <8 x i8> undef, <8 x i8> undef, i32 1) ret <8 x i8> %tmp4 } diff --git a/test/CodeGen/ARM/2010-05-21-BuildVector.ll b/test/CodeGen/ARM/2010-05-21-BuildVector.ll index ce959d1b91c8f..cd1c9c8c04214 100644 --- a/test/CodeGen/ARM/2010-05-21-BuildVector.ll +++ b/test/CodeGen/ARM/2010-05-21-BuildVector.ll @@ -36,8 +36,8 @@ entry: %tmp5 = insertelement <4 x float> %tmp7, float %18, i32 3 %19 = fmul <4 x float> %tmp5, %2 %20 = bitcast float* %fltp to i8* - tail call void @llvm.arm.neon.vst1.v4f32(i8* %20, <4 x float> %19) + tail call void @llvm.arm.neon.vst1.v4f32(i8* %20, <4 x float> %19, i32 1) ret void } -declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>) nounwind +declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>, i32) nounwind diff --git a/test/CodeGen/ARM/2010-06-11-vmovdrr-bitcast.ll b/test/CodeGen/ARM/2010-06-11-vmovdrr-bitcast.ll index e4f20990bed2d..6f487962310fe 100644 --- a/test/CodeGen/ARM/2010-06-11-vmovdrr-bitcast.ll +++ b/test/CodeGen/ARM/2010-06-11-vmovdrr-bitcast.ll @@ -12,8 +12,8 @@ entry: %tmp9 = trunc i128 %tmp8 to i64 ; <i64> [#uses=1] %tmp16.i = bitcast i64 %tmp6 to <8 x i8> ; <<8 x i8>> [#uses=1] %tmp20.i = bitcast i64 %tmp9 to <8 x i8> ; <<8 x i8>> [#uses=1] - tail call void @llvm.arm.neon.vst2.v8i8(i8* %b, <8 x i8> %tmp16.i, <8 x i8> %tmp20.i) nounwind + tail call void @llvm.arm.neon.vst2.v8i8(i8* %b, <8 x i8> %tmp16.i, <8 x i8> %tmp20.i, i32 1) nounwind ret void } -declare void @llvm.arm.neon.vst2.v8i8(i8*, <8 x i8>, <8 x i8>) nounwind +declare void @llvm.arm.neon.vst2.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind diff --git a/test/CodeGen/ARM/2010-06-21-nondarwin-tc.ll b/test/CodeGen/ARM/2010-06-21-nondarwin-tc.ll index 7650d883d7b1c..ac8e80904edae 100755 --- a/test/CodeGen/ARM/2010-06-21-nondarwin-tc.ll +++ b/test/CodeGen/ARM/2010-06-21-nondarwin-tc.ll @@ -1,5 +1,6 @@ ; RUN: llc < %s -march=arm -mtriple=armv4t-unknown-linux-gnueabi | FileCheck %s ; PR 7433 +; XFAIL: * %0 = type { i8*, i8* } %1 = type { i8*, i8*, i8* } diff --git a/test/CodeGen/ARM/2010-06-29-PartialRedefFastAlloc.ll b/test/CodeGen/ARM/2010-06-29-PartialRedefFastAlloc.ll index 0c5b180cf8464..ffc47ebdf1969 100644 --- a/test/CodeGen/ARM/2010-06-29-PartialRedefFastAlloc.ll +++ b/test/CodeGen/ARM/2010-06-29-PartialRedefFastAlloc.ll @@ -16,10 +16,10 @@ target triple = "thumbv7-apple-darwin10" define i32 @test(i8* %arg) nounwind { entry: - %0 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i8* %arg) + %0 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i8* %arg, i32 1) %1 = shufflevector <2 x i64> undef, <2 x i64> %0, <2 x i32> <i32 1, i32 2> store <2 x i64> %1, <2 x i64>* undef, align 16 ret i32 undef } -declare <2 x i64> @llvm.arm.neon.vld1.v2i64(i8*) nounwind readonly +declare <2 x i64> @llvm.arm.neon.vld1.v2i64(i8*, i32) nounwind readonly diff --git a/test/CodeGen/ARM/2010-07-26-GlobalMerge.ll b/test/CodeGen/ARM/2010-07-26-GlobalMerge.ll new file mode 100644 index 0000000000000..c03c815459465 --- /dev/null +++ b/test/CodeGen/ARM/2010-07-26-GlobalMerge.ll @@ -0,0 +1,95 @@ +; RUN: llc -enable-correct-eh-support < %s +; PR7716 +target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:64:64-v128:128:128-a0:0:32-n32" +target triple = "thumbv7-apple-darwin10.0.0" + +%0 = type { i8*, i8* } +%struct.A = type { i32 } + +@d = internal global i32 0, align 4 ; <i32*> [#uses=6] +@_ZTVN10__cxxabiv117__class_type_infoE = external global i8* ; <i8**> [#uses=1] +@_ZTS1A = internal constant [3 x i8] c"1A\00" ; <[3 x i8]*> [#uses=1] +@_ZTI1A = internal constant %0 { i8* bitcast (i8** getelementptr inbounds (i8** @_ZTVN10__cxxabiv117__class_type_infoE, i32 2) to i8*), i8* getelementptr inbounds ([3 x i8]* @_ZTS1A, i32 0, i32 0) } ; <%0*> [#uses=1] +@.str2 = private constant [18 x i8] c"c == %d, d == %d\0A\00" ; <[18 x i8]*> [#uses=1] +@.str3 = private constant [16 x i8] c"A(const A&) %d\0A\00" ; <[16 x i8]*> [#uses=1] +@.str4 = private constant [9 x i8] c"~A() %d\0A\00" ; <[9 x i8]*> [#uses=1] +@.str5 = private constant [8 x i8] c"A() %d\0A\00" ; <[8 x i8]*> [#uses=1] +@str = internal constant [14 x i8] c"Throwing 1...\00" ; <[14 x i8]*> [#uses=1] +@str1 = internal constant [8 x i8] c"Caught.\00" ; <[8 x i8]*> [#uses=1] + +declare i32 @printf(i8* nocapture, ...) nounwind + +declare i8* @__cxa_allocate_exception(i32) + +declare i8* @llvm.eh.exception() nounwind readonly + +declare i32 @__gxx_personality_sj0(...) + +declare i32 @llvm.eh.selector(i8*, i8*, ...) nounwind + +declare i32 @llvm.eh.typeid.for(i8*) nounwind + +declare void @_Unwind_SjLj_Resume(i8*) + +define internal void @_ZN1AD1Ev(%struct.A* nocapture %this) nounwind ssp align 2 { +entry: + %tmp.i = getelementptr inbounds %struct.A* %this, i32 0, i32 0 ; <i32*> [#uses=1] + %tmp2.i = load i32* %tmp.i ; <i32> [#uses=1] + %call.i = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([9 x i8]* @.str4, i32 0, i32 0), i32 %tmp2.i) nounwind ; <i32> [#uses=0] + %tmp3.i = load i32* @d ; <i32> [#uses=1] + %inc.i = add nsw i32 %tmp3.i, 1 ; <i32> [#uses=1] + store i32 %inc.i, i32* @d + ret void +} + +declare void @__cxa_throw(i8*, i8*, i8*) + +define i32 @main() ssp { +entry: + %puts.i = tail call i32 @puts(i8* getelementptr inbounds ([14 x i8]* @str, i32 0, i32 0)) ; <i32> [#uses=0] + %exception.i = tail call i8* @__cxa_allocate_exception(i32 4) nounwind ; <i8*> [#uses=2] + %tmp2.i.i.i = bitcast i8* %exception.i to i32* ; <i32*> [#uses=1] + store i32 1, i32* %tmp2.i.i.i + %call.i.i.i = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([8 x i8]* @.str5, i32 0, i32 0), i32 1) nounwind ; <i32> [#uses=0] + invoke void @__cxa_throw(i8* %exception.i, i8* bitcast (%0* @_ZTI1A to i8*), i8* bitcast (void (%struct.A*)* @_ZN1AD1Ev to i8*)) noreturn + to label %.noexc unwind label %lpad + +.noexc: ; preds = %entry + unreachable + +try.cont: ; preds = %lpad + %0 = tail call i8* @__cxa_get_exception_ptr(i8* %exn) nounwind ; <i8*> [#uses=0] + %call.i.i = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([16 x i8]* @.str3, i32 0, i32 0), i32 2) nounwind ; <i32> [#uses=0] + %1 = tail call i8* @__cxa_begin_catch(i8* %exn) nounwind ; <i8*> [#uses=0] + %puts = tail call i32 @puts(i8* getelementptr inbounds ([8 x i8]* @str1, i32 0, i32 0)) ; <i32> [#uses=0] + %call.i.i3 = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([9 x i8]* @.str4, i32 0, i32 0), i32 2) nounwind ; <i32> [#uses=0] + %tmp3.i.i = load i32* @d ; <i32> [#uses=1] + %inc.i.i4 = add nsw i32 %tmp3.i.i, 1 ; <i32> [#uses=1] + store i32 %inc.i.i4, i32* @d + tail call void @__cxa_end_catch() + %tmp13 = load i32* @d ; <i32> [#uses=1] + %call14 = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([18 x i8]* @.str2, i32 0, i32 0), i32 2, i32 %tmp13) ; <i32> [#uses=0] + %tmp16 = load i32* @d ; <i32> [#uses=1] + %cmp = icmp ne i32 %tmp16, 2 ; <i1> [#uses=1] + %conv = zext i1 %cmp to i32 ; <i32> [#uses=1] + ret i32 %conv + +lpad: ; preds = %entry + %exn = tail call i8* @llvm.eh.exception() nounwind ; <i8*> [#uses=4] + %eh.selector = tail call i32 (i8*, i8*, ...)* @llvm.eh.selector(i8* %exn, i8* bitcast (i32 (...)* @__gxx_personality_sj0 to i8*), i8* bitcast (%0* @_ZTI1A to i8*), i8* null) nounwind ; <i32> [#uses=1] + %2 = tail call i32 @llvm.eh.typeid.for(i8* bitcast (%0* @_ZTI1A to i8*)) nounwind ; <i32> [#uses=1] + %3 = icmp eq i32 %eh.selector, %2 ; <i1> [#uses=1] + br i1 %3, label %try.cont, label %eh.resume + +eh.resume: ; preds = %lpad + tail call void @_Unwind_SjLj_Resume(i8* %exn) noreturn + unreachable +} + +declare i8* @__cxa_get_exception_ptr(i8*) + +declare i8* @__cxa_begin_catch(i8*) + +declare void @__cxa_end_catch() + +declare i32 @puts(i8* nocapture) nounwind diff --git a/test/CodeGen/ARM/2010-08-04-EHCrash.ll b/test/CodeGen/ARM/2010-08-04-EHCrash.ll new file mode 100644 index 0000000000000..f57b7e6769494 --- /dev/null +++ b/test/CodeGen/ARM/2010-08-04-EHCrash.ll @@ -0,0 +1,65 @@ +; RUN: llc < %s -mtriple=thumbv7-apple-darwin10 +; <rdar://problem/8264008> + +define linkonce_odr arm_apcscc void @func1() { +entry: + %save_filt.936 = alloca i32 ; <i32*> [#uses=2] + %save_eptr.935 = alloca i8* ; <i8**> [#uses=2] + %eh_exception = alloca i8* ; <i8**> [#uses=5] + %eh_selector = alloca i32 ; <i32*> [#uses=3] + %"alloca point" = bitcast i32 0 to i32 ; <i32> [#uses=0] + call arm_apcscc void @func2() + br label %return + +bb: ; No predecessors! + %eh_select = load i32* %eh_selector ; <i32> [#uses=1] + store i32 %eh_select, i32* %save_filt.936, align 4 + %eh_value = load i8** %eh_exception ; <i8*> [#uses=1] + store i8* %eh_value, i8** %save_eptr.935, align 4 + invoke arm_apcscc void @func3() + to label %invcont unwind label %lpad + +invcont: ; preds = %bb + %tmp6 = load i8** %save_eptr.935, align 4 ; <i8*> [#uses=1] + store i8* %tmp6, i8** %eh_exception, align 4 + %tmp7 = load i32* %save_filt.936, align 4 ; <i32> [#uses=1] + store i32 %tmp7, i32* %eh_selector, align 4 + br label %Unwind + +bb12: ; preds = %ppad + call arm_apcscc void @_ZSt9terminatev() noreturn nounwind + unreachable + +return: ; preds = %entry + ret void + +lpad: ; preds = %bb + %eh_ptr = call i8* @llvm.eh.exception() ; <i8*> [#uses=1] + store i8* %eh_ptr, i8** %eh_exception + %eh_ptr13 = load i8** %eh_exception ; <i8*> [#uses=1] + %eh_select14 = call i32 (i8*, i8*, ...)* @llvm.eh.selector(i8* %eh_ptr13, i8* bitcast (i32 (...)* @__gxx_personality_sj0 to i8*), i32 1) + store i32 %eh_select14, i32* %eh_selector + br label %ppad + +ppad: + br label %bb12 + +Unwind: + %eh_ptr15 = load i8** %eh_exception + call arm_apcscc void @_Unwind_SjLj_Resume(i8* %eh_ptr15) + unreachable +} + +declare arm_apcscc void @func2() + +declare arm_apcscc void @_ZSt9terminatev() noreturn nounwind + +declare i8* @llvm.eh.exception() nounwind readonly + +declare i32 @llvm.eh.selector(i8*, i8*, ...) nounwind + +declare arm_apcscc void @_Unwind_SjLj_Resume(i8*) + +declare arm_apcscc void @func3() + +declare arm_apcscc i32 @__gxx_personality_sj0(...) diff --git a/test/CodeGen/ARM/arguments.ll b/test/CodeGen/ARM/arguments.ll index cc718399ea96e..bb7853e66ef46 100644 --- a/test/CodeGen/ARM/arguments.ll +++ b/test/CodeGen/ARM/arguments.ll @@ -1,11 +1,43 @@ -; RUN: llc < %s -mtriple=arm-linux-gnueabi | FileCheck %s -check-prefix=ELF -; RUN: llc < %s -mtriple=arm-apple-darwin | FileCheck %s -check-prefix=DARWIN +; RUN: llc < %s -mtriple=arm-linux-gnueabi -mattr=+vfp2 | FileCheck %s -check-prefix=ELF +; RUN: llc < %s -mtriple=arm-apple-darwin -mattr=+vfp2 | FileCheck %s -check-prefix=DARWIN -define i32 @f(i32 %a, i64 %b) { +define i32 @f1(i32 %a, i64 %b) { +; ELF: f1: ; ELF: mov r0, r2 +; DARWIN: f1: ; DARWIN: mov r0, r1 - %tmp = call i32 @g(i64 %b) + %tmp = call i32 @g1(i64 %b) ret i32 %tmp } -declare i32 @g(i64) +; test that allocating the double to r2/r3 makes r1 unavailable on gnueabi. +define i32 @f2() nounwind optsize { +; ELF: f2: +; ELF: mov r0, #128 +; ELF: str r0, [sp] +; DARWIN: f2: +; DARWIN: mov r3, #128 +entry: + %0 = tail call i32 (i32, ...)* @g2(i32 5, double 1.600000e+01, i32 128) nounwind optsize ; <i32> [#uses=1] + %not. = icmp ne i32 %0, 128 ; <i1> [#uses=1] + %.0 = zext i1 %not. to i32 ; <i32> [#uses=1] + ret i32 %.0 +} + +; test that on gnueabi a 64 bit value at this position will cause r3 to go +; unused and the value stored in [sp] +; ELF: f3: +; ELF: ldr r0, [sp] +; ELF-NEXT: mov pc, lr +; DARWIN: f3: +; DARWIN: mov r0, r3 +; DARWIN-NEXT: mov pc, lr +define i32 @f3(i32 %i, i32 %j, i32 %k, i64 %l, ...) { +entry: + %0 = trunc i64 %l to i32 + ret i32 %0 +} + +declare i32 @g1(i64) + +declare i32 @g2(i32 %i, ...) diff --git a/test/CodeGen/ARM/bfi.ll b/test/CodeGen/ARM/bfi.ll new file mode 100644 index 0000000000000..59e2b43a9172b --- /dev/null +++ b/test/CodeGen/ARM/bfi.ll @@ -0,0 +1,40 @@ +; RUN: llc -march=arm -mattr=+v6t2 < %s | FileCheck %s + +%struct.F = type { [3 x i8], i8 } + +@X = common global %struct.F zeroinitializer, align 4 ; <%struct.F*> [#uses=1] + +define void @f1([1 x i32] %f.coerce0) nounwind { +entry: +; CHECK: f1 +; CHECK: mov r2, #10 +; CHECK: bfi r1, r2, #22, #4 + %0 = load i32* bitcast (%struct.F* @X to i32*), align 4 ; <i32> [#uses=1] + %1 = and i32 %0, -62914561 ; <i32> [#uses=1] + %2 = or i32 %1, 41943040 ; <i32> [#uses=1] + store i32 %2, i32* bitcast (%struct.F* @X to i32*), align 4 + ret void +} + +define i32 @f2(i32 %A, i32 %B) nounwind readnone optsize { +entry: +; CHECK: f2 +; CHECK: mov r1, r1, lsr #7 +; CHECK: bfi r0, r1, #7, #16 + %and = and i32 %A, -8388481 ; <i32> [#uses=1] + %and2 = and i32 %B, 8388480 ; <i32> [#uses=1] + %or = or i32 %and2, %and ; <i32> [#uses=1] + ret i32 %or +} + +define i32 @f3(i32 %A, i32 %B) nounwind readnone optsize { +entry: +; CHECK: f3 +; CHECK: mov r2, r0, lsr #7 +; CHECK: mov r0, r1 +; CHECK: bfi r0, r2, #7, #16 + %and = and i32 %A, 8388480 ; <i32> [#uses=1] + %and2 = and i32 %B, -8388481 ; <i32> [#uses=1] + %or = or i32 %and2, %and ; <i32> [#uses=1] + ret i32 %or +} diff --git a/test/CodeGen/ARM/call-tc.ll b/test/CodeGen/ARM/call-tc.ll index f1269d5bd2be6..db5afe3f56cb8 100644 --- a/test/CodeGen/ARM/call-tc.ll +++ b/test/CodeGen/ARM/call-tc.ll @@ -2,6 +2,7 @@ ; RUN: llc < %s -march=arm -mtriple=arm-apple-darwin -mattr=+v5t | FileCheck %s -check-prefix=CHECKV5 ; RUN: llc < %s -march=arm -mtriple=arm-linux-gnueabi\ ; RUN: -relocation-model=pic | FileCheck %s -check-prefix=CHECKELF +; XFAIL: * @t = weak global i32 ()* null ; <i32 ()**> [#uses=1] diff --git a/test/CodeGen/ARM/code-placement.ll b/test/CodeGen/ARM/code-placement.ll new file mode 100644 index 0000000000000..25c556889fc44 --- /dev/null +++ b/test/CodeGen/ARM/code-placement.ll @@ -0,0 +1,29 @@ +; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s +; PHI elimination shouldn't break backedge. +; rdar://8263994 + +%struct.list_data_s = type { i16, i16 } +%struct.list_head = type { %struct.list_head*, %struct.list_data_s* } + +define arm_apcscc %struct.list_head* @t(%struct.list_head* %list) nounwind { +entry: + %0 = icmp eq %struct.list_head* %list, null + br i1 %0, label %bb2, label %bb + +bb: +; CHECK: LBB0_2: +; CHECK: bne LBB0_2 +; CHECK-NOT: b LBB0_2 +; CHECK: bx lr + %list_addr.05 = phi %struct.list_head* [ %2, %bb ], [ %list, %entry ] + %next.04 = phi %struct.list_head* [ %list_addr.05, %bb ], [ null, %entry ] + %1 = getelementptr inbounds %struct.list_head* %list_addr.05, i32 0, i32 0 + %2 = load %struct.list_head** %1, align 4 + store %struct.list_head* %next.04, %struct.list_head** %1, align 4 + %3 = icmp eq %struct.list_head* %2, null + br i1 %3, label %bb2, label %bb + +bb2: + %next.0.lcssa = phi %struct.list_head* [ null, %entry ], [ %list_addr.05, %bb ] + ret %struct.list_head* %next.0.lcssa +} diff --git a/test/CodeGen/ARM/div.ll b/test/CodeGen/ARM/div.ll index d833afa55583a..448b437ddf46e 100644 --- a/test/CodeGen/ARM/div.ll +++ b/test/CodeGen/ARM/div.ll @@ -1,13 +1,9 @@ ; RUN: llc < %s -march=arm | FileCheck %s -check-prefix=CHECK-ARM -; RUN: llc < %s -march=arm -mcpu=cortex-m3 \ -; RUN: | FileCheck %s -check-prefix=CHECK-ARMV7M define i32 @f1(i32 %a, i32 %b) { entry: ; CHECK-ARM: f1 ; CHECK-ARM: __divsi3 -; CHECK-ARMV7M: f1 -; CHECK-ARMV7M: sdiv %tmp1 = sdiv i32 %a, %b ; <i32> [#uses=1] ret i32 %tmp1 } @@ -16,8 +12,6 @@ define i32 @f2(i32 %a, i32 %b) { entry: ; CHECK-ARM: f2 ; CHECK-ARM: __udivsi3 -; CHECK-ARMV7M: f2 -; CHECK-ARMV7M: udiv %tmp1 = udiv i32 %a, %b ; <i32> [#uses=1] ret i32 %tmp1 } @@ -26,8 +20,6 @@ define i32 @f3(i32 %a, i32 %b) { entry: ; CHECK-ARM: f3 ; CHECK-ARM: __modsi3 -; CHECK-ARMV7M: f3 -; CHECK-ARMV7M: sdiv %tmp1 = srem i32 %a, %b ; <i32> [#uses=1] ret i32 %tmp1 } @@ -36,8 +28,6 @@ define i32 @f4(i32 %a, i32 %b) { entry: ; CHECK-ARM: f4 ; CHECK-ARM: __umodsi3 -; CHECK-ARMV7M: f4 -; CHECK-ARMV7M: udiv %tmp1 = urem i32 %a, %b ; <i32> [#uses=1] ret i32 %tmp1 } diff --git a/test/CodeGen/ARM/fast-isel.ll b/test/CodeGen/ARM/fast-isel.ll new file mode 100644 index 0000000000000..3bee84d84de4c --- /dev/null +++ b/test/CodeGen/ARM/fast-isel.ll @@ -0,0 +1,39 @@ +; RUN: llc < %s -O0 -arm-fast-isel -fast-isel-abort -mtriple=armv7-apple-darwin +; RUN: llc < %s -O0 -arm-fast-isel -fast-isel-abort -mtriple=thumbv7-apple-darwin + +; Very basic fast-isel functionality. + +define i32 @add(i32 %a, i32 %b) nounwind ssp { +entry: + %a.addr = alloca i32, align 4 + %b.addr = alloca i32, align 4 + store i32 %a, i32* %a.addr + store i32 %b, i32* %b.addr + %tmp = load i32* %a.addr + %tmp1 = load i32* %b.addr + %add = add nsw i32 %tmp, %tmp1 + ret i32 %add +} + +define i32* @foo(i32* %p, i32* %q, i32** %z) nounwind { +entry: + %r = load i32* %p + %s = load i32* %q + %y = load i32** %z + br label %fast + +fast: + %t0 = add i32 %r, %s + %t1 = mul i32 %t0, %s + %t2 = sub i32 %t1, %s + %t3 = and i32 %t2, %s + %t4 = xor i32 %t3, 3 + %t5 = xor i32 %t4, %s + %t6 = add i32 %t5, 2 + %t7 = getelementptr i32* %y, i32 1 + %t8 = getelementptr i32* %t7, i32 %t6 + br label %exit + +exit: + ret i32* %t8 +} diff --git a/test/CodeGen/ARM/fnmuls.ll b/test/CodeGen/ARM/fnmuls.ll index efd87d2dcb896..3223885feda90 100644 --- a/test/CodeGen/ARM/fnmuls.ll +++ b/test/CodeGen/ARM/fnmuls.ll @@ -1,20 +1,18 @@ -; XFAIL: * ; RUN: llc < %s -march=arm -mattr=+vfp2 | FileCheck %s -; RUN: llc < %s -march=arm -mattr=+neon -arm-use-neon-fp=1 | FileCheck %s -; RUN: llc < %s -march=arm -mattr=+neon -arm-use-neon-fp=0 | FileCheck %s +; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s ; RUN: llc < %s -march=arm -mcpu=cortex-a8 | FileCheck %s ; RUN: llc < %s -march=arm -mcpu=cortex-a9 | FileCheck %s -define float @test1(float %a, float %b) nounwind { -; CHECK: fnmscs s2, s1, s0 +define arm_aapcs_vfpcc float @test1(float %a, float %b) nounwind { +; CHECK: vnmul.f32 s0, s0, s1 entry: %0 = fmul float %a, %b %1 = fsub float -0.0, %0 ret float %1 } -define float @test2(float %a, float %b) nounwind { -; CHECK: fnmscs s2, s1, s0 +define arm_aapcs_vfpcc float @test2(float %a, float %b) nounwind { +; CHECK: vnmul.f32 s0, s0, s1 entry: %0 = fmul float %a, %b %1 = fmul float -1.0, %0 diff --git a/test/CodeGen/ARM/fpcmp-opt.ll b/test/CodeGen/ARM/fpcmp-opt.ll index 6875288304be2..64350591b87f1 100644 --- a/test/CodeGen/ARM/fpcmp-opt.ll +++ b/test/CodeGen/ARM/fpcmp-opt.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -march=arm -mcpu=cortex-a8 -mattr=+vfp2 -enable-unsafe-fp-math -enable-finite-only-fp-math | FileCheck -check-prefix=FINITE %s +; RUN: llc < %s -march=arm -mcpu=cortex-a8 -mattr=+vfp2 -enable-unsafe-fp-math -enable-no-nans-fp-math | FileCheck -check-prefix=FINITE %s ; RUN: llc < %s -march=arm -mcpu=cortex-a8 -mattr=+vfp2 -enable-unsafe-fp-math | FileCheck -check-prefix=NAN %s ; rdar://7461510 diff --git a/test/CodeGen/ARM/fpowi.ll b/test/CodeGen/ARM/fpowi.ll index 7f9d62a9e9453..561463720c808 100644 --- a/test/CodeGen/ARM/fpowi.ll +++ b/test/CodeGen/ARM/fpowi.ll @@ -3,7 +3,7 @@ ; ModuleID = '<stdin>' target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64" -target triple = "arm-linux-gnueabi" +target triple = "arm-unknown-linux-gnueabi" define double @_ZSt3powdi(double %__x, i32 %__i) { entry: diff --git a/test/CodeGen/ARM/long_shift.ll b/test/CodeGen/ARM/long_shift.ll index 688b7bc312c7b..1ec4d15f66723 100644 --- a/test/CodeGen/ARM/long_shift.ll +++ b/test/CodeGen/ARM/long_shift.ll @@ -24,8 +24,7 @@ define i32 @f2(i64 %x, i64 %y) { ; CHECK: f2 ; CHECK: mov r0, r0, lsr r2 ; CHECK-NEXT: rsb r3, r2, #32 -; CHECK-NEXT: sub r2, r2, #32 -; CHECK-NEXT: cmp r2, #0 +; CHECK-NEXT: subs r2, r2, #32 ; CHECK-NEXT: orr r0, r0, r1, lsl r3 ; CHECK-NEXT: movge r0, r1, asr r2 %a = ashr i64 %x, %y @@ -37,8 +36,7 @@ define i32 @f3(i64 %x, i64 %y) { ; CHECK: f3 ; CHECK: mov r0, r0, lsr r2 ; CHECK-NEXT: rsb r3, r2, #32 -; CHECK-NEXT: sub r2, r2, #32 -; CHECK-NEXT: cmp r2, #0 +; CHECK-NEXT: subs r2, r2, #32 ; CHECK-NEXT: orr r0, r0, r1, lsl r3 ; CHECK-NEXT: movge r0, r1, lsr r2 %a = lshr i64 %x, %y diff --git a/test/CodeGen/ARM/lsr-on-unrolled-loops.ll b/test/CodeGen/ARM/lsr-on-unrolled-loops.ll index 25cf1356d61c3..866be423c2cb1 100644 --- a/test/CodeGen/ARM/lsr-on-unrolled-loops.ll +++ b/test/CodeGen/ARM/lsr-on-unrolled-loops.ll @@ -4,14 +4,14 @@ ; constant offset addressing, so that each of the following stores ; uses the same register. -; CHECK: vstr.32 s0, [r9, #-128] -; CHECK: vstr.32 s0, [r9, #-96] -; CHECK: vstr.32 s0, [r9, #-64] -; CHECK: vstr.32 s0, [r9, #-32] -; CHECK: vstr.32 s0, [r9] -; CHECK: vstr.32 s0, [r9, #32] -; CHECK: vstr.32 s0, [r9, #64] -; CHECK: vstr.32 s0, [r9, #96] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #-128] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #-96] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #-64] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #-32] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #32] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #64] +; CHECK: vstr.32 s{{.*}}, [r{{.*}}, #96] target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:64:64-v128:128:128-a0:0:32-n32" @@ -628,8 +628,7 @@ bb24: ; preds = %bb23 ; CHECK: @ %bb24 ; CHECK-NEXT: @ in Loop: Header=BB1_1 Depth=1 -; CHECK-NEXT: sub{{.*}} [[REGISTER:r[0-9]+]], #1 -; CHECK-NEXT: cmp{{.*}} [[REGISTER]], #0 +; CHECK-NEXT: sub{{.*}} [[REGISTER:(r[0-9]+)|(lr)]], #1 ; CHECK-NEXT: bne.w %92 = icmp eq i32 %tmp81, %indvar78 ; <i1> [#uses=1] diff --git a/test/CodeGen/ARM/pack.ll b/test/CodeGen/ARM/pack.ll index 1e2e7aa0c8ff1..4905dc28cf488 100644 --- a/test/CodeGen/ARM/pack.ll +++ b/test/CodeGen/ARM/pack.ll @@ -1,8 +1,7 @@ -; RUN: llc < %s -march=arm -mattr=+v6 | \ -; RUN: grep pkhbt | count 5 -; RUN: llc < %s -march=arm -mattr=+v6 | \ -; RUN: grep pkhtb | count 4 +; RUN: llc < %s -march=arm -mattr=+v6 | FileCheck %s +; CHECK: test1 +; CHECK: pkhbt r0, r0, r1, lsl #16 define i32 @test1(i32 %X, i32 %Y) { %tmp1 = and i32 %X, 65535 ; <i32> [#uses=1] %tmp4 = shl i32 %Y, 16 ; <i32> [#uses=1] @@ -10,6 +9,8 @@ define i32 @test1(i32 %X, i32 %Y) { ret i32 %tmp5 } +; CHECK: test1a +; CHECK: pkhbt r0, r0, r1, lsl #16 define i32 @test1a(i32 %X, i32 %Y) { %tmp19 = and i32 %X, 65535 ; <i32> [#uses=1] %tmp37 = shl i32 %Y, 16 ; <i32> [#uses=1] @@ -17,6 +18,8 @@ define i32 @test1a(i32 %X, i32 %Y) { ret i32 %tmp5 } +; CHECK: test2 +; CHECK: pkhbt r0, r0, r1, lsl #12 define i32 @test2(i32 %X, i32 %Y) { %tmp1 = and i32 %X, 65535 ; <i32> [#uses=1] %tmp3 = shl i32 %Y, 12 ; <i32> [#uses=1] @@ -25,6 +28,8 @@ define i32 @test2(i32 %X, i32 %Y) { ret i32 %tmp57 } +; CHECK: test3 +; CHECK: pkhbt r0, r0, r1, lsl #18 define i32 @test3(i32 %X, i32 %Y) { %tmp19 = and i32 %X, 65535 ; <i32> [#uses=1] %tmp37 = shl i32 %Y, 18 ; <i32> [#uses=1] @@ -32,6 +37,8 @@ define i32 @test3(i32 %X, i32 %Y) { ret i32 %tmp5 } +; CHECK: test4 +; CHECK: pkhbt r0, r0, r1 define i32 @test4(i32 %X, i32 %Y) { %tmp1 = and i32 %X, 65535 ; <i32> [#uses=1] %tmp3 = and i32 %Y, -65536 ; <i32> [#uses=1] @@ -39,6 +46,8 @@ define i32 @test4(i32 %X, i32 %Y) { ret i32 %tmp46 } +; CHECK: test5 +; CHECK: pkhtb r0, r0, r1, asr #16 define i32 @test5(i32 %X, i32 %Y) { %tmp17 = and i32 %X, -65536 ; <i32> [#uses=1] %tmp2 = bitcast i32 %Y to i32 ; <i32> [#uses=1] @@ -47,6 +56,8 @@ define i32 @test5(i32 %X, i32 %Y) { ret i32 %tmp5 } +; CHECK: test5a +; CHECK: pkhtb r0, r0, r1, asr #16 define i32 @test5a(i32 %X, i32 %Y) { %tmp110 = and i32 %X, -65536 ; <i32> [#uses=1] %tmp37 = lshr i32 %Y, 16 ; <i32> [#uses=1] @@ -55,6 +66,8 @@ define i32 @test5a(i32 %X, i32 %Y) { ret i32 %tmp5 } +; CHECK: test6 +; CHECK: pkhtb r0, r0, r1, asr #12 define i32 @test6(i32 %X, i32 %Y) { %tmp1 = and i32 %X, -65536 ; <i32> [#uses=1] %tmp37 = lshr i32 %Y, 12 ; <i32> [#uses=1] @@ -64,6 +77,8 @@ define i32 @test6(i32 %X, i32 %Y) { ret i32 %tmp59 } +; CHECK: test7 +; CHECK: pkhtb r0, r0, r1, asr #18 define i32 @test7(i32 %X, i32 %Y) { %tmp1 = and i32 %X, -65536 ; <i32> [#uses=1] %tmp3 = ashr i32 %Y, 18 ; <i32> [#uses=1] @@ -71,3 +86,12 @@ define i32 @test7(i32 %X, i32 %Y) { %tmp57 = or i32 %tmp4, %tmp1 ; <i32> [#uses=1] ret i32 %tmp57 } + +; CHECK: test8 +; CHECK: pkhtb r0, r0, r1, asr #22 +define i32 @test8(i32 %X, i32 %Y) { + %tmp1 = and i32 %X, -65536 + %tmp3 = lshr i32 %Y, 22 + %tmp57 = or i32 %tmp3, %tmp1 + ret i32 %tmp57 +} diff --git a/test/CodeGen/ARM/reg_sequence.ll b/test/CodeGen/ARM/reg_sequence.ll index 89b657797f2a3..2e4f10d8a63de 100644 --- a/test/CodeGen/ARM/reg_sequence.ll +++ b/test/CodeGen/ARM/reg_sequence.ll @@ -23,21 +23,21 @@ entry: %2 = getelementptr inbounds %struct.int32x4_t* %vT1ptr, i32 0, i32 0 ; <<4 x i32>*> [#uses=1] %3 = load <4 x i32>* %2, align 16 ; <<4 x i32>> [#uses=1] %4 = bitcast i16* %i_ptr to i8* ; <i8*> [#uses=1] - %5 = tail call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %4) ; <<8 x i16>> [#uses=1] + %5 = tail call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %4, i32 1) ; <<8 x i16>> [#uses=1] %6 = bitcast <8 x i16> %5 to <2 x double> ; <<2 x double>> [#uses=2] %7 = extractelement <2 x double> %6, i32 0 ; <double> [#uses=1] %8 = bitcast double %7 to <4 x i16> ; <<4 x i16>> [#uses=1] - %9 = tail call <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16> %8) ; <<4 x i32>> [#uses=1] + %9 = sext <4 x i16> %8 to <4 x i32> ; <<4 x i32>> [#uses=1] %10 = extractelement <2 x double> %6, i32 1 ; <double> [#uses=1] %11 = bitcast double %10 to <4 x i16> ; <<4 x i16>> [#uses=1] - %12 = tail call <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16> %11) ; <<4 x i32>> [#uses=1] + %12 = sext <4 x i16> %11 to <4 x i32> ; <<4 x i32>> [#uses=1] %13 = mul <4 x i32> %1, %9 ; <<4 x i32>> [#uses=1] %14 = mul <4 x i32> %3, %12 ; <<4 x i32>> [#uses=1] %15 = tail call <4 x i16> @llvm.arm.neon.vshiftn.v4i16(<4 x i32> %13, <4 x i32> <i32 -12, i32 -12, i32 -12, i32 -12>) ; <<4 x i16>> [#uses=1] %16 = tail call <4 x i16> @llvm.arm.neon.vshiftn.v4i16(<4 x i32> %14, <4 x i32> <i32 -12, i32 -12, i32 -12, i32 -12>) ; <<4 x i16>> [#uses=1] %17 = shufflevector <4 x i16> %15, <4 x i16> %16, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; <<8 x i16>> [#uses=1] %18 = bitcast i16* %o_ptr to i8* ; <i8*> [#uses=1] - tail call void @llvm.arm.neon.vst1.v8i16(i8* %18, <8 x i16> %17) + tail call void @llvm.arm.neon.vst1.v8i16(i8* %18, <8 x i16> %17, i32 1) ret void } @@ -45,10 +45,10 @@ define void @t2(i16* %i_ptr, i16* %o_ptr, %struct.int16x8_t* nocapture %vT0ptr, entry: ; CHECK: t2: ; CHECK: vld1.16 -; CHECK: vmul.i16 ; CHECK-NOT: vmov ; CHECK: vld1.16 ; CHECK: vmul.i16 +; CHECK: vmul.i16 ; CHECK-NOT: vmov ; CHECK: vst1.16 ; CHECK: vst1.16 @@ -57,17 +57,17 @@ entry: %2 = getelementptr inbounds %struct.int16x8_t* %vT1ptr, i32 0, i32 0 ; <<8 x i16>*> [#uses=1] %3 = load <8 x i16>* %2, align 16 ; <<8 x i16>> [#uses=1] %4 = bitcast i16* %i_ptr to i8* ; <i8*> [#uses=1] - %5 = tail call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %4) ; <<8 x i16>> [#uses=1] + %5 = tail call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %4, i32 1) ; <<8 x i16>> [#uses=1] %6 = getelementptr inbounds i16* %i_ptr, i32 8 ; <i16*> [#uses=1] %7 = bitcast i16* %6 to i8* ; <i8*> [#uses=1] - %8 = tail call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %7) ; <<8 x i16>> [#uses=1] + %8 = tail call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %7, i32 1) ; <<8 x i16>> [#uses=1] %9 = mul <8 x i16> %1, %5 ; <<8 x i16>> [#uses=1] %10 = mul <8 x i16> %3, %8 ; <<8 x i16>> [#uses=1] %11 = bitcast i16* %o_ptr to i8* ; <i8*> [#uses=1] - tail call void @llvm.arm.neon.vst1.v8i16(i8* %11, <8 x i16> %9) + tail call void @llvm.arm.neon.vst1.v8i16(i8* %11, <8 x i16> %9, i32 1) %12 = getelementptr inbounds i16* %o_ptr, i32 8 ; <i16*> [#uses=1] %13 = bitcast i16* %12 to i8* ; <i8*> [#uses=1] - tail call void @llvm.arm.neon.vst1.v8i16(i8* %13, <8 x i16> %10) + tail call void @llvm.arm.neon.vst1.v8i16(i8* %13, <8 x i16> %10, i32 1) ret void } @@ -77,14 +77,14 @@ define <8 x i8> @t3(i8* %A, i8* %B) nounwind { ; CHECK: vmul.i8 ; CHECK-NOT: vmov ; CHECK: vst3.8 - %tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A) ; <%struct.__neon_int8x8x3_t> [#uses=2] + %tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=2] %tmp2 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 0 ; <<8 x i8>> [#uses=1] %tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 2 ; <<8 x i8>> [#uses=1] %tmp4 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 1 ; <<8 x i8>> [#uses=1] %tmp5 = sub <8 x i8> %tmp3, %tmp4 %tmp6 = add <8 x i8> %tmp2, %tmp3 ; <<8 x i8>> [#uses=1] %tmp7 = mul <8 x i8> %tmp4, %tmp2 - tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> %tmp5, <8 x i8> %tmp6, <8 x i8> %tmp7) + tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> %tmp5, <8 x i8> %tmp6, <8 x i8> %tmp7, i32 1) ret <8 x i8> %tmp4 } @@ -97,10 +97,10 @@ entry: ; CHECK-NOT: vmov ; CHECK: bne %tmp1 = bitcast i32* %in to i8* ; <i8*> [#uses=1] - %tmp2 = tail call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp1) ; <%struct.__neon_int32x4x2_t> [#uses=2] + %tmp2 = tail call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp1, i32 1) ; <%struct.__neon_int32x4x2_t> [#uses=2] %tmp3 = getelementptr inbounds i32* %in, i32 8 ; <i32*> [#uses=1] %tmp4 = bitcast i32* %tmp3 to i8* ; <i8*> [#uses=1] - %tmp5 = tail call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp4) ; <%struct.__neon_int32x4x2_t> [#uses=2] + %tmp5 = tail call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp4, i32 1) ; <%struct.__neon_int32x4x2_t> [#uses=2] %tmp8 = bitcast i32* %out to i8* ; <i8*> [#uses=1] br i1 undef, label %return1, label %return2 @@ -116,7 +116,7 @@ return1: %tmp39 = extractvalue %struct.__neon_int32x4x2_t %tmp5, 1 ; <<4 x i32>> [#uses=1] %tmp6 = add <4 x i32> %tmp52, %tmp ; <<4 x i32>> [#uses=1] %tmp7 = add <4 x i32> %tmp57, %tmp39 ; <<4 x i32>> [#uses=1] - tail call void @llvm.arm.neon.vst2.v4i32(i8* %tmp8, <4 x i32> %tmp6, <4 x i32> %tmp7) + tail call void @llvm.arm.neon.vst2.v4i32(i8* %tmp8, <4 x i32> %tmp6, <4 x i32> %tmp7, i32 1) ret void return2: @@ -128,7 +128,7 @@ return2: %tmp100 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 0 ; <<4 x i32>> [#uses=1] %tmp101 = extractvalue %struct.__neon_int32x4x2_t %tmp5, 1 ; <<4 x i32>> [#uses=1] %tmp102 = add <4 x i32> %tmp100, %tmp101 ; <<4 x i32>> [#uses=1] - tail call void @llvm.arm.neon.vst2.v4i32(i8* %tmp8, <4 x i32> %tmp102, <4 x i32> %tmp101) + tail call void @llvm.arm.neon.vst2.v4i32(i8* %tmp8, <4 x i32> %tmp102, <4 x i32> %tmp101, i32 1) call void @llvm.trap() unreachable } @@ -143,7 +143,7 @@ define <8 x i16> @t5(i16* %A, <8 x i16>* %B) nounwind { ; CHECK: vadd.i16 %tmp0 = bitcast i16* %A to i8* ; <i8*> [#uses=1] %tmp1 = load <8 x i16>* %B ; <<8 x i16>> [#uses=2] - %tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) ; <%struct.__neon_int16x8x2_t> [#uses=2] + %tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 1) ; <%struct.__neon_int16x8x2_t> [#uses=2] %tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 0 ; <<8 x i16>> [#uses=1] %tmp4 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 1 ; <<8 x i16>> [#uses=1] %tmp5 = add <8 x i16> %tmp3, %tmp4 ; <<8 x i16>> [#uses=1] @@ -156,7 +156,7 @@ define <8 x i8> @t6(i8* %A, <8 x i8>* %B) nounwind { ; CHECK: vmov d1, d0 ; CHECK-NEXT: vld2.8 {d0[1], d1[1]} %tmp1 = load <8 x i8>* %B ; <<8 x i8>> [#uses=2] - %tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) ; <%struct.__neon_int8x8x2_t> [#uses=2] + %tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) ; <%struct.__neon_int8x8x2_t> [#uses=2] %tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 0 ; <<8 x i8>> [#uses=1] %tmp4 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 1 ; <<8 x i8>> [#uses=1] %tmp5 = add <8 x i8> %tmp3, %tmp4 ; <<8 x i8>> [#uses=1] @@ -174,14 +174,14 @@ entry: ; CHECK: vuzp.32 q0, q1 ; CHECK: vst1.32 %0 = bitcast i32* %iptr to i8* ; <i8*> [#uses=2] - %1 = tail call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %0) ; <%struct.__neon_int32x4x2_t> [#uses=2] + %1 = tail call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %0, i32 1) ; <%struct.__neon_int32x4x2_t> [#uses=2] %tmp57 = extractvalue %struct.__neon_int32x4x2_t %1, 0 ; <<4 x i32>> [#uses=1] %tmp60 = extractvalue %struct.__neon_int32x4x2_t %1, 1 ; <<4 x i32>> [#uses=1] %2 = bitcast i32* %optr to i8* ; <i8*> [#uses=2] - tail call void @llvm.arm.neon.vst2.v4i32(i8* %2, <4 x i32> %tmp57, <4 x i32> %tmp60) - %3 = tail call <4 x i32> @llvm.arm.neon.vld1.v4i32(i8* %0) ; <<4 x i32>> [#uses=1] + tail call void @llvm.arm.neon.vst2.v4i32(i8* %2, <4 x i32> %tmp57, <4 x i32> %tmp60, i32 1) + %3 = tail call <4 x i32> @llvm.arm.neon.vld1.v4i32(i8* %0, i32 1) ; <<4 x i32>> [#uses=1] %4 = shufflevector <4 x i32> %3, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 0, i32 2> ; <<4 x i32>> [#uses=1] - tail call void @llvm.arm.neon.vst1.v4i32(i8* %2, <4 x i32> %4) + tail call void @llvm.arm.neon.vst1.v4i32(i8* %2, <4 x i32> %4, i32 1) ret void } @@ -304,44 +304,43 @@ bb14: ; preds = %bb6 ; This test crashes the coalescer because live variables were not updated properly. define <8 x i8> @t11(i8* %A1, i8* %A2, i8* %A3, i8* %A4, i8* %A5, i8* %A6, i8* %A7, i8* %A8, i8* %B) nounwind { - %tmp1d = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A4) ; <%struct.__neon_int8x8x3_t> [#uses=1] + %tmp1d = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A4, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=1] %tmp2d = extractvalue %struct.__neon_int8x8x3_t %tmp1d, 0 ; <<8 x i8>> [#uses=1] - %tmp1f = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A6) ; <%struct.__neon_int8x8x3_t> [#uses=1] + %tmp1f = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A6, i32 1) ; <%struct.__neon_int8x8x3_t> [#uses=1] %tmp2f = extractvalue %struct.__neon_int8x8x3_t %tmp1f, 0 ; <<8 x i8>> [#uses=1] %tmp2bd = add <8 x i8> zeroinitializer, %tmp2d ; <<8 x i8>> [#uses=1] %tmp2abcd = mul <8 x i8> zeroinitializer, %tmp2bd ; <<8 x i8>> [#uses=1] %tmp2ef = sub <8 x i8> zeroinitializer, %tmp2f ; <<8 x i8>> [#uses=1] %tmp2efgh = mul <8 x i8> %tmp2ef, undef ; <<8 x i8>> [#uses=2] - call void @llvm.arm.neon.vst3.v8i8(i8* %A2, <8 x i8> undef, <8 x i8> undef, <8 x i8> %tmp2efgh) + call void @llvm.arm.neon.vst3.v8i8(i8* %A2, <8 x i8> undef, <8 x i8> undef, <8 x i8> %tmp2efgh, i32 1) %tmp2 = sub <8 x i8> %tmp2efgh, %tmp2abcd ; <<8 x i8>> [#uses=1] %tmp7 = mul <8 x i8> undef, %tmp2 ; <<8 x i8>> [#uses=1] - tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> undef, <8 x i8> undef, <8 x i8> %tmp7) + tail call void @llvm.arm.neon.vst3.v8i8(i8* %B, <8 x i8> undef, <8 x i8> undef, <8 x i8> %tmp7, i32 1) ret <8 x i8> undef } -declare <4 x i32> @llvm.arm.neon.vld1.v4i32(i8*) nounwind readonly - -declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*) nounwind readonly +declare <4 x i32> @llvm.arm.neon.vld1.v4i32(i8*, i32) nounwind readonly -declare <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16>) nounwind readnone +declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*, i32) nounwind readonly declare <4 x i16> @llvm.arm.neon.vshiftn.v4i16(<4 x i32>, <4 x i32>) nounwind readnone -declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>) nounwind +declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>) nounwind +declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind +declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) +nounwind -declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*) nounwind readonly +declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*, i32) nounwind readonly -declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8*) nounwind readonly +declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8*, i32) nounwind readonly -declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind readonly +declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly -declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32) nounwind readonly +declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32, i32) nounwind readonly -declare void @llvm.arm.neon.vst2.v4i32(i8*, <4 x i32>, <4 x i32>) nounwind +declare void @llvm.arm.neon.vst2.v4i32(i8*, <4 x i32>, <4 x i32>, i32) nounwind declare <4 x float> @llvm.arm.neon.vrsqrte.v4f32(<4 x float>) nounwind readnone diff --git a/test/CodeGen/ARM/remat.ll b/test/CodeGen/ARM/remat.ll index 1e780e6a9097d..6b86f1a9f368d 100644 --- a/test/CodeGen/ARM/remat.ll +++ b/test/CodeGen/ARM/remat.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -march=arm -mattr=+v6,+vfp2 -stats -info-output-file - | grep "Number of re-materialization" +; RUN: llc < %s -march=arm -mattr=+v6,+vfp2 -o /dev/null -stats -info-output-file - | grep "Number of re-materialization" define i32 @main(i32 %argc, i8** nocapture %argv, double %d1, double %d2) nounwind { entry: diff --git a/test/CodeGen/ARM/select.ll b/test/CodeGen/ARM/select.ll index 29c55c6bd9752..7413bed5c5b17 100644 --- a/test/CodeGen/ARM/select.ll +++ b/test/CodeGen/ARM/select.ll @@ -1,5 +1,6 @@ ; RUN: llc < %s -march=arm | FileCheck %s ; RUN: llc < %s -march=arm -mattr=+vfp2 | FileCheck %s --check-prefix=CHECK-VFP +; RUN: llc < %s -mattr=+neon,+thumb2 -mtriple=thumbv7-apple-darwin | FileCheck %s --check-prefix=CHECK-NEON define i32 @f1(i32 %a.s) { ;CHECK: f1: @@ -65,3 +66,27 @@ define double @f7(double %a, double %b) { %tmp1 = select i1 %tmp, double -1.000e+00, double %b ret double %tmp1 } + +; <rdar://problem/7260094> +; +; We used to generate really horrible code for this function. The main cause was +; a lack of a custom lowering routine for an ISD::SELECT. This would result in +; two "it" blocks in the code: one for the "icmp" and another to move the index +; into the constant pool based on the value of the "icmp". If we have one "it" +; block generated, odds are good that we have close to the ideal code for this: +; +; CHECK-NEON: _f8: +; CHECK-NEON: movw [[REGISTER_1:r[0-9]+]], #1123 +; CHECK-NEON-NEXT: movs [[REGISTER_2:r[0-9]+]], #0 +; CHECK-NEON-NEXT: cmp r0, [[REGISTER_1]] +; CHECK-NEON-NEXT: adr [[REGISTER_3:r[0-9]+]], #LCPI +; CHECK-NEON-NEXT: it eq +; CHECK-NEON-NEXT: moveq [[REGISTER_2]], #4 +; CHECK-NEON-NEXT: ldr +; CHECK-NEON: bx + +define arm_apcscc float @f8(i32 %a) nounwind { + %tmp = icmp eq i32 %a, 1123 + %tmp1 = select i1 %tmp, float 0x3FF3BE76C0000000, float 0x40030E9A20000000 + ret float %tmp1 +} diff --git a/test/CodeGen/ARM/spill-q.ll b/test/CodeGen/ARM/spill-q.ll index 792ef79982b79..ae1ba2f738252 100644 --- a/test/CodeGen/ARM/spill-q.ll +++ b/test/CodeGen/ARM/spill-q.ll @@ -7,7 +7,7 @@ %quux = type { i32 (...)**, %baz*, i32 } %quuz = type { %quux, i32, %bar, [128 x i8], [16 x %foo], %foo, %foo, %foo } -declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*) nounwind readonly +declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*, i32) nounwind readonly define void @aaa(%quuz* %this, i8* %block) { ; CHECK: aaa: @@ -15,11 +15,11 @@ define void @aaa(%quuz* %this, i8* %block) { ; CHECK: vst1.64 {{.*}}sp, :128 ; CHECK: vld1.64 {{.*}}sp, :128 entry: - %0 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef) nounwind ; <<4 x float>> [#uses=1] + %0 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1] store float 6.300000e+01, float* undef, align 4 - %1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef) nounwind ; <<4 x float>> [#uses=1] + %1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1] store float 0.000000e+00, float* undef, align 4 - %2 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef) nounwind ; <<4 x float>> [#uses=1] + %2 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1] %val173 = load <4 x float>* undef ; <<4 x float>> [#uses=1] br label %bb4 diff --git a/test/CodeGen/ARM/t2-imm.ll b/test/CodeGen/ARM/t2-imm.ll index 848a4dfed0542..8b4145914e7ca 100644 --- a/test/CodeGen/ARM/t2-imm.ll +++ b/test/CodeGen/ARM/t2-imm.ll @@ -1,9 +1,9 @@ -; RUN: llc < %s -march=arm -mattr=+thumb2 | FileCheck %s +; RUN: llc < %s -march=thumb -mattr=+thumb2 | FileCheck %s define i32 @f6(i32 %a) { ; CHECK:f6 -; CHECK: movw r0, #:lower16:65537123 -; CHECK: movt r0, #:upper16:65537123 +; CHECK: movw r0, #1123 +; CHECK: movt r0, #1000 %tmp = add i32 0, 65537123 ret i32 %tmp } diff --git a/test/CodeGen/ARM/vaba.ll b/test/CodeGen/ARM/vaba.ll index e2dca4647bce6..4fe1c434799d2 100644 --- a/test/CodeGen/ARM/vaba.ll +++ b/test/CodeGen/ARM/vaba.ll @@ -6,8 +6,9 @@ define <8 x i8> @vabas8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i8> @llvm.arm.neon.vabas.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i8> %tmp4 + %tmp4 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3) + %tmp5 = add <8 x i8> %tmp1, %tmp4 + ret <8 x i8> %tmp5 } define <4 x i16> @vabas16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -16,8 +17,9 @@ define <4 x i16> @vabas16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i16> @llvm.arm.neon.vabas.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i16> %tmp4 + %tmp4 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3) + %tmp5 = add <4 x i16> %tmp1, %tmp4 + ret <4 x i16> %tmp5 } define <2 x i32> @vabas32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -26,8 +28,9 @@ define <2 x i32> @vabas32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i32> @llvm.arm.neon.vabas.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i32> %tmp4 + %tmp4 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3) + %tmp5 = add <2 x i32> %tmp1, %tmp4 + ret <2 x i32> %tmp5 } define <8 x i8> @vabau8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { @@ -36,8 +39,9 @@ define <8 x i8> @vabau8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i8> @llvm.arm.neon.vabau.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i8> %tmp4 + %tmp4 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3) + %tmp5 = add <8 x i8> %tmp1, %tmp4 + ret <8 x i8> %tmp5 } define <4 x i16> @vabau16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -46,8 +50,9 @@ define <4 x i16> @vabau16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i16> @llvm.arm.neon.vabau.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i16> %tmp4 + %tmp4 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3) + %tmp5 = add <4 x i16> %tmp1, %tmp4 + ret <4 x i16> %tmp5 } define <2 x i32> @vabau32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -56,8 +61,9 @@ define <2 x i32> @vabau32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i32> @llvm.arm.neon.vabau.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i32> %tmp4 + %tmp4 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3) + %tmp5 = add <2 x i32> %tmp1, %tmp4 + ret <2 x i32> %tmp5 } define <16 x i8> @vabaQs8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind { @@ -66,8 +72,9 @@ define <16 x i8> @vabaQs8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind %tmp1 = load <16 x i8>* %A %tmp2 = load <16 x i8>* %B %tmp3 = load <16 x i8>* %C - %tmp4 = call <16 x i8> @llvm.arm.neon.vabas.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i8> %tmp3) - ret <16 x i8> %tmp4 + %tmp4 = call <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8> %tmp2, <16 x i8> %tmp3) + %tmp5 = add <16 x i8> %tmp1, %tmp4 + ret <16 x i8> %tmp5 } define <8 x i16> @vabaQs16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind { @@ -76,8 +83,9 @@ define <8 x i16> @vabaQs16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i16>* %B %tmp3 = load <8 x i16>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vabas.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i16> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = call <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16> %tmp2, <8 x i16> %tmp3) + %tmp5 = add <8 x i16> %tmp1, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vabaQs32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind { @@ -86,8 +94,9 @@ define <4 x i32> @vabaQs32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i32>* %B %tmp3 = load <4 x i32>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vabas.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = call <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32> %tmp2, <4 x i32> %tmp3) + %tmp5 = add <4 x i32> %tmp1, %tmp4 + ret <4 x i32> %tmp5 } define <16 x i8> @vabaQu8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind { @@ -96,8 +105,9 @@ define <16 x i8> @vabaQu8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind %tmp1 = load <16 x i8>* %A %tmp2 = load <16 x i8>* %B %tmp3 = load <16 x i8>* %C - %tmp4 = call <16 x i8> @llvm.arm.neon.vabau.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i8> %tmp3) - ret <16 x i8> %tmp4 + %tmp4 = call <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8> %tmp2, <16 x i8> %tmp3) + %tmp5 = add <16 x i8> %tmp1, %tmp4 + ret <16 x i8> %tmp5 } define <8 x i16> @vabaQu16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind { @@ -106,8 +116,9 @@ define <8 x i16> @vabaQu16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i16>* %B %tmp3 = load <8 x i16>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vabau.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i16> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = call <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16> %tmp2, <8 x i16> %tmp3) + %tmp5 = add <8 x i16> %tmp1, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vabaQu32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind { @@ -116,25 +127,26 @@ define <4 x i32> @vabaQu32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i32>* %B %tmp3 = load <4 x i32>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vabau.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = call <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32> %tmp2, <4 x i32> %tmp3) + %tmp5 = add <4 x i32> %tmp1, %tmp4 + ret <4 x i32> %tmp5 } -declare <8 x i8> @llvm.arm.neon.vabas.v8i8(<8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i16> @llvm.arm.neon.vabas.v4i16(<4 x i16>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i32> @llvm.arm.neon.vabas.v2i32(<2 x i32>, <2 x i32>, <2 x i32>) nounwind readnone +declare <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8>, <8 x i8>) nounwind readnone +declare <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16>, <4 x i16>) nounwind readnone +declare <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32>, <2 x i32>) nounwind readnone -declare <8 x i8> @llvm.arm.neon.vabau.v8i8(<8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i16> @llvm.arm.neon.vabau.v4i16(<4 x i16>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i32> @llvm.arm.neon.vabau.v2i32(<2 x i32>, <2 x i32>, <2 x i32>) nounwind readnone +declare <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone +declare <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone +declare <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone -declare <16 x i8> @llvm.arm.neon.vabas.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone -declare <8 x i16> @llvm.arm.neon.vabas.v8i16(<8 x i16>, <8 x i16>, <8 x i16>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vabas.v4i32(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone +declare <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8>, <16 x i8>) nounwind readnone +declare <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16>, <8 x i16>) nounwind readnone +declare <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32>, <4 x i32>) nounwind readnone -declare <16 x i8> @llvm.arm.neon.vabau.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone -declare <8 x i16> @llvm.arm.neon.vabau.v8i16(<8 x i16>, <8 x i16>, <8 x i16>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vabau.v4i32(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone +declare <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone +declare <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone +declare <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone define <8 x i16> @vabals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { ;CHECK: vabals8: @@ -142,8 +154,10 @@ define <8 x i16> @vabals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vabals.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3) + %tmp5 = zext <8 x i8> %tmp4 to <8 x i16> + %tmp6 = add <8 x i16> %tmp1, %tmp5 + ret <8 x i16> %tmp6 } define <4 x i32> @vabals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -152,8 +166,10 @@ define <4 x i32> @vabals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vabals.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3) + %tmp5 = zext <4 x i16> %tmp4 to <4 x i32> + %tmp6 = add <4 x i32> %tmp1, %tmp5 + ret <4 x i32> %tmp6 } define <2 x i64> @vabals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -162,8 +178,10 @@ define <2 x i64> @vabals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i64> @llvm.arm.neon.vabals.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i64> %tmp4 + %tmp4 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3) + %tmp5 = zext <2 x i32> %tmp4 to <2 x i64> + %tmp6 = add <2 x i64> %tmp1, %tmp5 + ret <2 x i64> %tmp6 } define <8 x i16> @vabalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { @@ -172,8 +190,10 @@ define <8 x i16> @vabalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vabalu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3) + %tmp5 = zext <8 x i8> %tmp4 to <8 x i16> + %tmp6 = add <8 x i16> %tmp1, %tmp5 + ret <8 x i16> %tmp6 } define <4 x i32> @vabalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -182,8 +202,10 @@ define <4 x i32> @vabalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vabalu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3) + %tmp5 = zext <4 x i16> %tmp4 to <4 x i32> + %tmp6 = add <4 x i32> %tmp1, %tmp5 + ret <4 x i32> %tmp6 } define <2 x i64> @vabalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -192,14 +214,8 @@ define <2 x i64> @vabalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i64> @llvm.arm.neon.vabalu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i64> %tmp4 + %tmp4 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3) + %tmp5 = zext <2 x i32> %tmp4 to <2 x i64> + %tmp6 = add <2 x i64> %tmp1, %tmp5 + ret <2 x i64> %tmp6 } - -declare <8 x i16> @llvm.arm.neon.vabals.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vabals.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vabals.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vabalu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vabalu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vabalu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone diff --git a/test/CodeGen/ARM/vabd.ll b/test/CodeGen/ARM/vabd.ll index 2b4539361459b..9ec734fa7641e 100644 --- a/test/CodeGen/ARM/vabd.ll +++ b/test/CodeGen/ARM/vabd.ll @@ -151,8 +151,9 @@ define <8 x i16> @vabdls8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vabdl.s8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vabdls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2) + %tmp4 = zext <8 x i8> %tmp3 to <8 x i16> + ret <8 x i16> %tmp4 } define <4 x i32> @vabdls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -160,8 +161,9 @@ define <4 x i32> @vabdls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vabdl.s16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vabdls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2) + %tmp4 = zext <4 x i16> %tmp3 to <4 x i32> + ret <4 x i32> %tmp4 } define <2 x i64> @vabdls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -169,8 +171,9 @@ define <2 x i64> @vabdls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vabdl.s32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vabdls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2) + %tmp4 = zext <2 x i32> %tmp3 to <2 x i64> + ret <2 x i64> %tmp4 } define <8 x i16> @vabdlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { @@ -178,8 +181,9 @@ define <8 x i16> @vabdlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vabdl.u8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vabdlu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2) + %tmp4 = zext <8 x i8> %tmp3 to <8 x i16> + ret <8 x i16> %tmp4 } define <4 x i32> @vabdlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -187,8 +191,9 @@ define <4 x i32> @vabdlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vabdl.u16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vabdlu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2) + %tmp4 = zext <4 x i16> %tmp3 to <4 x i32> + ret <4 x i32> %tmp4 } define <2 x i64> @vabdlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -196,14 +201,7 @@ define <2 x i64> @vabdlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vabdl.u32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vabdlu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2) + %tmp4 = zext <2 x i32> %tmp3 to <2 x i64> + ret <2 x i64> %tmp4 } - -declare <8 x i16> @llvm.arm.neon.vabdls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vabdls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vabdls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vabdlu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vabdlu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vabdlu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone diff --git a/test/CodeGen/ARM/vadd.ll b/test/CodeGen/ARM/vadd.ll index 9bb8bf5610453..a830e968ff788 100644 --- a/test/CodeGen/ARM/vadd.ll +++ b/test/CodeGen/ARM/vadd.ll @@ -157,8 +157,10 @@ define <8 x i16> @vaddls8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vaddl.s8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vaddls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = sext <8 x i8> %tmp1 to <8 x i16> + %tmp4 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = add <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vaddls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -166,8 +168,10 @@ define <4 x i32> @vaddls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vaddl.s16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vaddls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = sext <4 x i16> %tmp1 to <4 x i32> + %tmp4 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = add <4 x i32> %tmp3, %tmp4 + ret <4 x i32> %tmp5 } define <2 x i64> @vaddls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -175,8 +179,10 @@ define <2 x i64> @vaddls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vaddl.s32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vaddls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = sext <2 x i32> %tmp1 to <2 x i64> + %tmp4 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = add <2 x i64> %tmp3, %tmp4 + ret <2 x i64> %tmp5 } define <8 x i16> @vaddlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { @@ -184,8 +190,10 @@ define <8 x i16> @vaddlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vaddl.u8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vaddlu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = zext <8 x i8> %tmp1 to <8 x i16> + %tmp4 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = add <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vaddlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -193,8 +201,10 @@ define <4 x i32> @vaddlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vaddl.u16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vaddlu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = zext <4 x i16> %tmp1 to <4 x i32> + %tmp4 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = add <4 x i32> %tmp3, %tmp4 + ret <4 x i32> %tmp5 } define <2 x i64> @vaddlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -202,25 +212,20 @@ define <2 x i64> @vaddlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vaddl.u32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vaddlu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = zext <2 x i32> %tmp1 to <2 x i64> + %tmp4 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = add <2 x i64> %tmp3, %tmp4 + ret <2 x i64> %tmp5 } -declare <8 x i16> @llvm.arm.neon.vaddls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vaddls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vaddls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vaddlu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vaddlu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vaddlu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - define <8 x i16> @vaddws8(<8 x i16>* %A, <8 x i8>* %B) nounwind { ;CHECK: vaddws8: ;CHECK: vaddw.s8 %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vaddws.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp4 = add <8 x i16> %tmp1, %tmp3 + ret <8 x i16> %tmp4 } define <4 x i32> @vaddws16(<4 x i32>* %A, <4 x i16>* %B) nounwind { @@ -228,8 +233,9 @@ define <4 x i32> @vaddws16(<4 x i32>* %A, <4 x i16>* %B) nounwind { ;CHECK: vaddw.s16 %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vaddws.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp4 = add <4 x i32> %tmp1, %tmp3 + ret <4 x i32> %tmp4 } define <2 x i64> @vaddws32(<2 x i64>* %A, <2 x i32>* %B) nounwind { @@ -237,8 +243,9 @@ define <2 x i64> @vaddws32(<2 x i64>* %A, <2 x i32>* %B) nounwind { ;CHECK: vaddw.s32 %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vaddws.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp4 = add <2 x i64> %tmp1, %tmp3 + ret <2 x i64> %tmp4 } define <8 x i16> @vaddwu8(<8 x i16>* %A, <8 x i8>* %B) nounwind { @@ -246,8 +253,9 @@ define <8 x i16> @vaddwu8(<8 x i16>* %A, <8 x i8>* %B) nounwind { ;CHECK: vaddw.u8 %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vaddwu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp4 = add <8 x i16> %tmp1, %tmp3 + ret <8 x i16> %tmp4 } define <4 x i32> @vaddwu16(<4 x i32>* %A, <4 x i16>* %B) nounwind { @@ -255,8 +263,9 @@ define <4 x i32> @vaddwu16(<4 x i32>* %A, <4 x i16>* %B) nounwind { ;CHECK: vaddw.u16 %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vaddwu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp4 = add <4 x i32> %tmp1, %tmp3 + ret <4 x i32> %tmp4 } define <2 x i64> @vaddwu32(<2 x i64>* %A, <2 x i32>* %B) nounwind { @@ -264,14 +273,7 @@ define <2 x i64> @vaddwu32(<2 x i64>* %A, <2 x i32>* %B) nounwind { ;CHECK: vaddw.u32 %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vaddwu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp4 = add <2 x i64> %tmp1, %tmp3 + ret <2 x i64> %tmp4 } - -declare <8 x i16> @llvm.arm.neon.vaddws.v8i16(<8 x i16>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vaddws.v4i32(<4 x i32>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vaddws.v2i64(<2 x i64>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vaddwu.v8i16(<8 x i16>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vaddwu.v4i32(<4 x i32>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vaddwu.v2i64(<2 x i64>, <2 x i32>) nounwind readnone diff --git a/test/CodeGen/ARM/vext.ll b/test/CodeGen/ARM/vext.ll index c11a67c6c4341..e460a84f6265f 100644 --- a/test/CodeGen/ARM/vext.ll +++ b/test/CodeGen/ARM/vext.ll @@ -54,3 +54,23 @@ define <4 x i32> @test_vextq32(<4 x i32>* %A, <4 x i32>* %B) nounwind { ret <4 x i32> %tmp3 } +; Undef shuffle indices should not prevent matching to VEXT: + +define <8 x i8> @test_vextd_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind { +;CHECK: test_vextd_undef: +;CHECK: vext + %tmp1 = load <8 x i8>* %A + %tmp2 = load <8 x i8>* %B + %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 3, i32 undef, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10> + ret <8 x i8> %tmp3 +} + +define <16 x i8> @test_vextRq_undef(<16 x i8>* %A, <16 x i8>* %B) nounwind { +;CHECK: test_vextRq_undef: +;CHECK: vext + %tmp1 = load <16 x i8>* %A + %tmp2 = load <16 x i8>* %B + %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 23, i32 24, i32 25, i32 26, i32 undef, i32 undef, i32 29, i32 30, i32 31, i32 0, i32 1, i32 2, i32 3, i32 4, i32 undef, i32 6> + ret <16 x i8> %tmp3 +} + diff --git a/test/CodeGen/ARM/vld1.ll b/test/CodeGen/ARM/vld1.ll index c61ea8c9a7892..2488e8a0d0ccc 100644 --- a/test/CodeGen/ARM/vld1.ll +++ b/test/CodeGen/ARM/vld1.ll @@ -3,7 +3,7 @@ define <8 x i8> @vld1i8(i8* %A) nounwind { ;CHECK: vld1i8: ;CHECK: vld1.8 - %tmp1 = call <8 x i8> @llvm.arm.neon.vld1.v8i8(i8* %A) + %tmp1 = call <8 x i8> @llvm.arm.neon.vld1.v8i8(i8* %A, i32 1) ret <8 x i8> %tmp1 } @@ -11,7 +11,7 @@ define <4 x i16> @vld1i16(i16* %A) nounwind { ;CHECK: vld1i16: ;CHECK: vld1.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i8* %tmp0) + %tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i8* %tmp0, i32 1) ret <4 x i16> %tmp1 } @@ -19,7 +19,7 @@ define <2 x i32> @vld1i32(i32* %A) nounwind { ;CHECK: vld1i32: ;CHECK: vld1.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i8* %tmp0) + %tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i8* %tmp0, i32 1) ret <2 x i32> %tmp1 } @@ -27,7 +27,7 @@ define <2 x float> @vld1f(float* %A) nounwind { ;CHECK: vld1f: ;CHECK: vld1.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call <2 x float> @llvm.arm.neon.vld1.v2f32(i8* %tmp0) + %tmp1 = call <2 x float> @llvm.arm.neon.vld1.v2f32(i8* %tmp0, i32 1) ret <2 x float> %tmp1 } @@ -35,14 +35,14 @@ define <1 x i64> @vld1i64(i64* %A) nounwind { ;CHECK: vld1i64: ;CHECK: vld1.64 %tmp0 = bitcast i64* %A to i8* - %tmp1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64(i8* %tmp0) + %tmp1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64(i8* %tmp0, i32 1) ret <1 x i64> %tmp1 } define <16 x i8> @vld1Qi8(i8* %A) nounwind { ;CHECK: vld1Qi8: ;CHECK: vld1.8 - %tmp1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %A) + %tmp1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %A, i32 1) ret <16 x i8> %tmp1 } @@ -50,7 +50,7 @@ define <8 x i16> @vld1Qi16(i16* %A) nounwind { ;CHECK: vld1Qi16: ;CHECK: vld1.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %tmp0) + %tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %tmp0, i32 1) ret <8 x i16> %tmp1 } @@ -58,7 +58,7 @@ define <4 x i32> @vld1Qi32(i32* %A) nounwind { ;CHECK: vld1Qi32: ;CHECK: vld1.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32(i8* %tmp0) + %tmp1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32(i8* %tmp0, i32 1) ret <4 x i32> %tmp1 } @@ -66,7 +66,7 @@ define <4 x float> @vld1Qf(float* %A) nounwind { ;CHECK: vld1Qf: ;CHECK: vld1.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* %tmp0) + %tmp1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* %tmp0, i32 1) ret <4 x float> %tmp1 } @@ -74,18 +74,31 @@ define <2 x i64> @vld1Qi64(i64* %A) nounwind { ;CHECK: vld1Qi64: ;CHECK: vld1.64 %tmp0 = bitcast i64* %A to i8* - %tmp1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i8* %tmp0) + %tmp1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i8* %tmp0, i32 1) ret <2 x i64> %tmp1 } -declare <8 x i8> @llvm.arm.neon.vld1.v8i8(i8*) nounwind readonly -declare <4 x i16> @llvm.arm.neon.vld1.v4i16(i8*) nounwind readonly -declare <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*) nounwind readonly -declare <2 x float> @llvm.arm.neon.vld1.v2f32(i8*) nounwind readonly -declare <1 x i64> @llvm.arm.neon.vld1.v1i64(i8*) nounwind readonly +declare <8 x i8> @llvm.arm.neon.vld1.v8i8(i8*, i32) nounwind readonly +declare <4 x i16> @llvm.arm.neon.vld1.v4i16(i8*, i32) nounwind readonly +declare <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*, i32) nounwind readonly +declare <2 x float> @llvm.arm.neon.vld1.v2f32(i8*, i32) nounwind readonly +declare <1 x i64> @llvm.arm.neon.vld1.v1i64(i8*, i32) nounwind readonly -declare <16 x i8> @llvm.arm.neon.vld1.v16i8(i8*) nounwind readonly -declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*) nounwind readonly -declare <4 x i32> @llvm.arm.neon.vld1.v4i32(i8*) nounwind readonly -declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*) nounwind readonly -declare <2 x i64> @llvm.arm.neon.vld1.v2i64(i8*) nounwind readonly +declare <16 x i8> @llvm.arm.neon.vld1.v16i8(i8*, i32) nounwind readonly +declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*, i32) nounwind readonly +declare <4 x i32> @llvm.arm.neon.vld1.v4i32(i8*, i32) nounwind readonly +declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*, i32) nounwind readonly +declare <2 x i64> @llvm.arm.neon.vld1.v2i64(i8*, i32) nounwind readonly + +; Radar 8355607 +; Do not crash if the vld1 result is not used. +define void @unused_vld1_result() { +entry: +;CHECK: unused_vld1_result +;CHECK: vld1.32 + %0 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) + call void @llvm.trap() + unreachable +} + +declare void @llvm.trap() nounwind diff --git a/test/CodeGen/ARM/vld2.ll b/test/CodeGen/ARM/vld2.ll index 0838636ce7421..811f6e6db96f2 100644 --- a/test/CodeGen/ARM/vld2.ll +++ b/test/CodeGen/ARM/vld2.ll @@ -14,7 +14,7 @@ define <8 x i8> @vld2i8(i8* %A) nounwind { ;CHECK: vld2i8: ;CHECK: vld2.8 - %tmp1 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8* %A) + %tmp1 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8* %A, i32 1) %tmp2 = extractvalue %struct.__neon_int8x8x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp1, 1 %tmp4 = add <8 x i8> %tmp2, %tmp3 @@ -25,7 +25,7 @@ define <4 x i16> @vld2i16(i16* %A) nounwind { ;CHECK: vld2i16: ;CHECK: vld2.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8* %tmp0) + %tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 1 %tmp4 = add <4 x i16> %tmp2, %tmp3 @@ -36,7 +36,7 @@ define <2 x i32> @vld2i32(i32* %A) nounwind { ;CHECK: vld2i32: ;CHECK: vld2.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8* %tmp0) + %tmp1 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int32x2x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp1, 1 %tmp4 = add <2 x i32> %tmp2, %tmp3 @@ -47,7 +47,7 @@ define <2 x float> @vld2f(float* %A) nounwind { ;CHECK: vld2f: ;CHECK: vld2.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8* %tmp0) + %tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 1 %tmp4 = fadd <2 x float> %tmp2, %tmp3 @@ -58,7 +58,7 @@ define <1 x i64> @vld2i64(i64* %A) nounwind { ;CHECK: vld2i64: ;CHECK: vld1.64 %tmp0 = bitcast i64* %A to i8* - %tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8* %tmp0) + %tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 1 %tmp4 = add <1 x i64> %tmp2, %tmp3 @@ -68,7 +68,7 @@ define <1 x i64> @vld2i64(i64* %A) nounwind { define <16 x i8> @vld2Qi8(i8* %A) nounwind { ;CHECK: vld2Qi8: ;CHECK: vld2.8 - %tmp1 = call %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8* %A) + %tmp1 = call %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8* %A, i32 1) %tmp2 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int8x16x2_t %tmp1, 1 %tmp4 = add <16 x i8> %tmp2, %tmp3 @@ -79,7 +79,7 @@ define <8 x i16> @vld2Qi16(i16* %A) nounwind { ;CHECK: vld2Qi16: ;CHECK: vld2.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8* %tmp0) + %tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 1 %tmp4 = add <8 x i16> %tmp2, %tmp3 @@ -90,7 +90,7 @@ define <4 x i32> @vld2Qi32(i32* %A) nounwind { ;CHECK: vld2Qi32: ;CHECK: vld2.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp0) + %tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 1 %tmp4 = add <4 x i32> %tmp2, %tmp3 @@ -101,20 +101,20 @@ define <4 x float> @vld2Qf(float* %A) nounwind { ;CHECK: vld2Qf: ;CHECK: vld2.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8* %tmp0) + %tmp1 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_float32x4x2_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp1, 1 %tmp4 = fadd <4 x float> %tmp2, %tmp3 ret <4 x float> %tmp4 } -declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8*) nounwind readonly -declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8*) nounwind readonly -declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8*) nounwind readonly -declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8*) nounwind readonly -declare %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8*) nounwind readonly +declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2.v8i8(i8*, i32) nounwind readonly +declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8*, i32) nounwind readonly +declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8*, i32) nounwind readonly +declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8*, i32) nounwind readonly +declare %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8*, i32) nounwind readonly -declare %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8*) nounwind readonly -declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8*) nounwind readonly -declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8*) nounwind readonly -declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8*) nounwind readonly +declare %struct.__neon_int8x16x2_t @llvm.arm.neon.vld2.v16i8(i8*, i32) nounwind readonly +declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8*, i32) nounwind readonly +declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8*, i32) nounwind readonly +declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8*, i32) nounwind readonly diff --git a/test/CodeGen/ARM/vld3.ll b/test/CodeGen/ARM/vld3.ll index 65a24486bc62c..92538c34f5b8e 100644 --- a/test/CodeGen/ARM/vld3.ll +++ b/test/CodeGen/ARM/vld3.ll @@ -14,7 +14,7 @@ define <8 x i8> @vld3i8(i8* %A) nounwind { ;CHECK: vld3i8: ;CHECK: vld3.8 - %tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A) + %tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A, i32 1) %tmp2 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 2 %tmp4 = add <8 x i8> %tmp2, %tmp3 @@ -25,7 +25,7 @@ define <4 x i16> @vld3i16(i16* %A) nounwind { ;CHECK: vld3i16: ;CHECK: vld3.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i8* %tmp0) + %tmp1 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int16x4x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp1, 2 %tmp4 = add <4 x i16> %tmp2, %tmp3 @@ -36,7 +36,7 @@ define <2 x i32> @vld3i32(i32* %A) nounwind { ;CHECK: vld3i32: ;CHECK: vld3.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3.v2i32(i8* %tmp0) + %tmp1 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3.v2i32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int32x2x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int32x2x3_t %tmp1, 2 %tmp4 = add <2 x i32> %tmp2, %tmp3 @@ -47,7 +47,7 @@ define <2 x float> @vld3f(float* %A) nounwind { ;CHECK: vld3f: ;CHECK: vld3.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3.v2f32(i8* %tmp0) + %tmp1 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3.v2f32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_float32x2x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_float32x2x3_t %tmp1, 2 %tmp4 = fadd <2 x float> %tmp2, %tmp3 @@ -58,7 +58,7 @@ define <1 x i64> @vld3i64(i64* %A) nounwind { ;CHECK: vld3i64: ;CHECK: vld1.64 %tmp0 = bitcast i64* %A to i8* - %tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8* %tmp0) + %tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 2 %tmp4 = add <1 x i64> %tmp2, %tmp3 @@ -69,7 +69,7 @@ define <16 x i8> @vld3Qi8(i8* %A) nounwind { ;CHECK: vld3Qi8: ;CHECK: vld3.8 ;CHECK: vld3.8 - %tmp1 = call %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8* %A) + %tmp1 = call %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8* %A, i32 1) %tmp2 = extractvalue %struct.__neon_int8x16x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int8x16x3_t %tmp1, 2 %tmp4 = add <16 x i8> %tmp2, %tmp3 @@ -81,7 +81,7 @@ define <8 x i16> @vld3Qi16(i16* %A) nounwind { ;CHECK: vld3.16 ;CHECK: vld3.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3.v8i16(i8* %tmp0) + %tmp1 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3.v8i16(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int16x8x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp1, 2 %tmp4 = add <8 x i16> %tmp2, %tmp3 @@ -93,7 +93,7 @@ define <4 x i32> @vld3Qi32(i32* %A) nounwind { ;CHECK: vld3.32 ;CHECK: vld3.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i8* %tmp0) + %tmp1 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int32x4x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp1, 2 %tmp4 = add <4 x i32> %tmp2, %tmp3 @@ -105,20 +105,20 @@ define <4 x float> @vld3Qf(float* %A) nounwind { ;CHECK: vld3.32 ;CHECK: vld3.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3.v4f32(i8* %tmp0) + %tmp1 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3.v4f32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_float32x4x3_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_float32x4x3_t %tmp1, 2 %tmp4 = fadd <4 x float> %tmp2, %tmp3 ret <4 x float> %tmp4 } -declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*) nounwind readonly -declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i8*) nounwind readonly -declare %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3.v2i32(i8*) nounwind readonly -declare %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3.v2f32(i8*) nounwind readonly -declare %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8*) nounwind readonly +declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8*, i32) nounwind readonly +declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i8*, i32) nounwind readonly +declare %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3.v2i32(i8*, i32) nounwind readonly +declare %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3.v2f32(i8*, i32) nounwind readonly +declare %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8*, i32) nounwind readonly -declare %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8*) nounwind readonly -declare %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3.v8i16(i8*) nounwind readonly -declare %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i8*) nounwind readonly -declare %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3.v4f32(i8*) nounwind readonly +declare %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8*, i32) nounwind readonly +declare %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3.v8i16(i8*, i32) nounwind readonly +declare %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i8*, i32) nounwind readonly +declare %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3.v4f32(i8*, i32) nounwind readonly diff --git a/test/CodeGen/ARM/vld4.ll b/test/CodeGen/ARM/vld4.ll index e0b870638a182..d1bf957ebadca 100644 --- a/test/CodeGen/ARM/vld4.ll +++ b/test/CodeGen/ARM/vld4.ll @@ -14,7 +14,7 @@ define <8 x i8> @vld4i8(i8* %A) nounwind { ;CHECK: vld4i8: ;CHECK: vld4.8 - %tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8* %A) + %tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8* %A, i32 1) %tmp2 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 2 %tmp4 = add <8 x i8> %tmp2, %tmp3 @@ -25,7 +25,7 @@ define <4 x i16> @vld4i16(i16* %A) nounwind { ;CHECK: vld4i16: ;CHECK: vld4.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8* %tmp0) + %tmp1 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 2 %tmp4 = add <4 x i16> %tmp2, %tmp3 @@ -36,7 +36,7 @@ define <2 x i32> @vld4i32(i32* %A) nounwind { ;CHECK: vld4i32: ;CHECK: vld4.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8* %tmp0) + %tmp1 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 2 %tmp4 = add <2 x i32> %tmp2, %tmp3 @@ -47,7 +47,7 @@ define <2 x float> @vld4f(float* %A) nounwind { ;CHECK: vld4f: ;CHECK: vld4.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8* %tmp0) + %tmp1 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_float32x2x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp1, 2 %tmp4 = fadd <2 x float> %tmp2, %tmp3 @@ -58,7 +58,7 @@ define <1 x i64> @vld4i64(i64* %A) nounwind { ;CHECK: vld4i64: ;CHECK: vld1.64 %tmp0 = bitcast i64* %A to i8* - %tmp1 = call %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8* %tmp0) + %tmp1 = call %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 2 %tmp4 = add <1 x i64> %tmp2, %tmp3 @@ -69,7 +69,7 @@ define <16 x i8> @vld4Qi8(i8* %A) nounwind { ;CHECK: vld4Qi8: ;CHECK: vld4.8 ;CHECK: vld4.8 - %tmp1 = call %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8* %A) + %tmp1 = call %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8* %A, i32 1) %tmp2 = extractvalue %struct.__neon_int8x16x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int8x16x4_t %tmp1, 2 %tmp4 = add <16 x i8> %tmp2, %tmp3 @@ -81,7 +81,7 @@ define <8 x i16> @vld4Qi16(i16* %A) nounwind { ;CHECK: vld4.16 ;CHECK: vld4.16 %tmp0 = bitcast i16* %A to i8* - %tmp1 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8* %tmp0) + %tmp1 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 2 %tmp4 = add <8 x i16> %tmp2, %tmp3 @@ -93,7 +93,7 @@ define <4 x i32> @vld4Qi32(i32* %A) nounwind { ;CHECK: vld4.32 ;CHECK: vld4.32 %tmp0 = bitcast i32* %A to i8* - %tmp1 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8* %tmp0) + %tmp1 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_int32x4x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp1, 2 %tmp4 = add <4 x i32> %tmp2, %tmp3 @@ -105,20 +105,20 @@ define <4 x float> @vld4Qf(float* %A) nounwind { ;CHECK: vld4.32 ;CHECK: vld4.32 %tmp0 = bitcast float* %A to i8* - %tmp1 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8* %tmp0) + %tmp1 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8* %tmp0, i32 1) %tmp2 = extractvalue %struct.__neon_float32x4x4_t %tmp1, 0 %tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp1, 2 %tmp4 = fadd <4 x float> %tmp2, %tmp3 ret <4 x float> %tmp4 } -declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8*) nounwind readonly -declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8*) nounwind readonly -declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8*) nounwind readonly -declare %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8*) nounwind readonly -declare %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8*) nounwind readonly +declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8*, i32) nounwind readonly +declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8*, i32) nounwind readonly +declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8*, i32) nounwind readonly +declare %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8*, i32) nounwind readonly +declare %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8*, i32) nounwind readonly -declare %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8*) nounwind readonly -declare %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8*) nounwind readonly -declare %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8*) nounwind readonly -declare %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8*) nounwind readonly +declare %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8*, i32) nounwind readonly +declare %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8*, i32) nounwind readonly +declare %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8*, i32) nounwind readonly +declare %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8*, i32) nounwind readonly diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll index b32c59019f4cb..31ee64fa598f9 100644 --- a/test/CodeGen/ARM/vldlane.ll +++ b/test/CodeGen/ARM/vldlane.ll @@ -13,7 +13,7 @@ define <8 x i8> @vld2lanei8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vld2lanei8: ;CHECK: vld2.8 %tmp1 = load <8 x i8>* %B - %tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 1 %tmp5 = add <8 x i8> %tmp3, %tmp4 @@ -25,7 +25,7 @@ define <4 x i16> @vld2lanei16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vld2.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - %tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 1 %tmp5 = add <4 x i16> %tmp3, %tmp4 @@ -37,7 +37,7 @@ define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vld2.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - %tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 1 %tmp5 = add <2 x i32> %tmp3, %tmp4 @@ -49,7 +49,7 @@ define <2 x float> @vld2lanef(float* %A, <2 x float>* %B) nounwind { ;CHECK: vld2.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - %tmp2 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) + %tmp2 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 1 %tmp5 = fadd <2 x float> %tmp3, %tmp4 @@ -61,7 +61,7 @@ define <8 x i16> @vld2laneQi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vld2.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - %tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 1 %tmp5 = add <8 x i16> %tmp3, %tmp4 @@ -73,7 +73,7 @@ define <4 x i32> @vld2laneQi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vld2.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - %tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2) + %tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 1) %tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 1 %tmp5 = add <4 x i32> %tmp3, %tmp4 @@ -85,21 +85,21 @@ define <4 x float> @vld2laneQf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vld2.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - %tmp2 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) + %tmp2 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 1 %tmp5 = fadd <4 x float> %tmp3, %tmp4 ret <4 x float> %tmp5 } -declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind readonly -declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind readonly -declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind readonly -declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind readonly +declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly +declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly +declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly +declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8*, <2 x float>, <2 x float>, i32, i32) nounwind readonly -declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32) nounwind readonly -declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32) nounwind readonly -declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8*, <4 x float>, <4 x float>, i32) nounwind readonly +declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32, i32) nounwind readonly +declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32, i32) nounwind readonly +declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8*, <4 x float>, <4 x float>, i32, i32) nounwind readonly %struct.__neon_int8x8x3_t = type { <8 x i8>, <8 x i8>, <8 x i8> } %struct.__neon_int16x4x3_t = type { <4 x i16>, <4 x i16>, <4 x i16> } @@ -114,7 +114,7 @@ define <8 x i8> @vld3lanei8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vld3lanei8: ;CHECK: vld3.8 %tmp1 = load <8 x i8>* %B - %tmp2 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 2 @@ -128,7 +128,7 @@ define <4 x i16> @vld3lanei16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vld3.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - %tmp2 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 2 @@ -142,7 +142,7 @@ define <2 x i32> @vld3lanei32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vld3.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - %tmp2 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 2 @@ -156,7 +156,7 @@ define <2 x float> @vld3lanef(float* %A, <2 x float>* %B) nounwind { ;CHECK: vld3.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - %tmp2 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) + %tmp2 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 2 @@ -170,7 +170,7 @@ define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vld3.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - %tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 2 @@ -184,7 +184,7 @@ define <4 x i32> @vld3laneQi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vld3.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - %tmp2 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 3) + %tmp2 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 3, i32 1) %tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 2 @@ -198,7 +198,7 @@ define <4 x float> @vld3laneQf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vld3.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - %tmp2 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) + %tmp2 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 2 @@ -207,14 +207,14 @@ define <4 x float> @vld3laneQf(float* %A, <4 x float>* %B) nounwind { ret <4 x float> %tmp7 } -declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind readonly -declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind readonly -declare %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind readonly -declare %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind readonly +declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly +declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly +declare %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly +declare %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind readonly -declare %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind readonly -declare %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind readonly -declare %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind readonly +declare %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind readonly +declare %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind readonly +declare %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind readonly %struct.__neon_int8x8x4_t = type { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %struct.__neon_int16x4x4_t = type { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @@ -229,7 +229,7 @@ define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vld4lanei8: ;CHECK: vld4.8 %tmp1 = load <8 x i8>* %B - %tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 2 @@ -245,7 +245,7 @@ define <4 x i16> @vld4lanei16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vld4.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - %tmp2 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 2 @@ -261,7 +261,7 @@ define <2 x i32> @vld4lanei32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vld4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - %tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 2 @@ -277,7 +277,7 @@ define <2 x float> @vld4lanef(float* %A, <2 x float>* %B) nounwind { ;CHECK: vld4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - %tmp2 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) + %tmp2 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 2 @@ -293,7 +293,7 @@ define <8 x i16> @vld4laneQi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vld4.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - %tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 2 @@ -309,7 +309,7 @@ define <4 x i32> @vld4laneQi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vld4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - %tmp2 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1) + %tmp2 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 2 @@ -325,7 +325,7 @@ define <4 x float> @vld4laneQf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vld4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - %tmp2 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) + %tmp2 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1) %tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 0 %tmp4 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 1 %tmp5 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 2 @@ -336,11 +336,11 @@ define <4 x float> @vld4laneQf(float* %A, <4 x float>* %B) nounwind { ret <4 x float> %tmp9 } -declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind readonly -declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind readonly -declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind readonly -declare %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind readonly +declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly +declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind readonly +declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly +declare %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind readonly -declare %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind readonly -declare %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind readonly -declare %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind readonly +declare %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind readonly +declare %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind readonly +declare %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind readonly diff --git a/test/CodeGen/ARM/vmla.ll b/test/CodeGen/ARM/vmla.ll index 77cf10ad3e684..9c6b210be7976 100644 --- a/test/CodeGen/ARM/vmla.ll +++ b/test/CodeGen/ARM/vmla.ll @@ -94,8 +94,11 @@ define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = sext <8 x i8> %tmp3 to <8 x i16> + %tmp6 = mul <8 x i16> %tmp4, %tmp5 + %tmp7 = add <8 x i16> %tmp1, %tmp6 + ret <8 x i16> %tmp7 } define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -104,8 +107,11 @@ define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = sext <4 x i16> %tmp3 to <4 x i32> + %tmp6 = mul <4 x i32> %tmp4, %tmp5 + %tmp7 = add <4 x i32> %tmp1, %tmp6 + ret <4 x i32> %tmp7 } define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -114,8 +120,11 @@ define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i64> %tmp4 + %tmp4 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = sext <2 x i32> %tmp3 to <2 x i64> + %tmp6 = mul <2 x i64> %tmp4, %tmp5 + %tmp7 = add <2 x i64> %tmp1, %tmp6 + ret <2 x i64> %tmp7 } define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { @@ -124,8 +133,11 @@ define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = zext <8 x i8> %tmp3 to <8 x i16> + %tmp6 = mul <8 x i16> %tmp4, %tmp5 + %tmp7 = add <8 x i16> %tmp1, %tmp6 + ret <8 x i16> %tmp7 } define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -134,8 +146,11 @@ define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = zext <4 x i16> %tmp3 to <4 x i32> + %tmp6 = mul <4 x i32> %tmp4, %tmp5 + %tmp7 = add <4 x i32> %tmp1, %tmp6 + ret <4 x i32> %tmp7 } define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -144,8 +159,11 @@ define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i64> %tmp4 + %tmp4 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = zext <2 x i32> %tmp3 to <2 x i64> + %tmp6 = mul <2 x i64> %tmp4, %tmp5 + %tmp7 = add <2 x i64> %tmp1, %tmp6 + ret <2 x i64> %tmp7 } define arm_aapcs_vfpcc <4 x i32> @test_vmlal_lanes16(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %arg2_int16x4_t) nounwind readnone { @@ -153,8 +171,11 @@ entry: ; CHECK: test_vmlal_lanes16 ; CHECK: vmlal.s16 q0, d2, d3[1] %0 = shufflevector <4 x i16> %arg2_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1] - %1 = tail call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1] - ret <4 x i32> %1 + %1 = sext <4 x i16> %arg1_int16x4_t to <4 x i32> + %2 = sext <4 x i16> %0 to <4 x i32> + %3 = mul <4 x i32> %1, %2 + %4 = add <4 x i32> %arg0_int32x4_t, %3 + ret <4 x i32> %4 } define arm_aapcs_vfpcc <2 x i64> @test_vmlal_lanes32(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %arg2_int32x2_t) nounwind readnone { @@ -162,8 +183,11 @@ entry: ; CHECK: test_vmlal_lanes32 ; CHECK: vmlal.s32 q0, d2, d3[1] %0 = shufflevector <2 x i32> %arg2_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1] - %1 = tail call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1] - ret <2 x i64> %1 + %1 = sext <2 x i32> %arg1_int32x2_t to <2 x i64> + %2 = sext <2 x i32> %0 to <2 x i64> + %3 = mul <2 x i64> %1, %2 + %4 = add <2 x i64> %arg0_int64x2_t, %3 + ret <2 x i64> %4 } define arm_aapcs_vfpcc <4 x i32> @test_vmlal_laneu16(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %arg2_uint16x4_t) nounwind readnone { @@ -171,8 +195,11 @@ entry: ; CHECK: test_vmlal_laneu16 ; CHECK: vmlal.u16 q0, d2, d3[1] %0 = shufflevector <4 x i16> %arg2_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1] - %1 = tail call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1] - ret <4 x i32> %1 + %1 = zext <4 x i16> %arg1_uint16x4_t to <4 x i32> + %2 = zext <4 x i16> %0 to <4 x i32> + %3 = mul <4 x i32> %1, %2 + %4 = add <4 x i32> %arg0_uint32x4_t, %3 + ret <4 x i32> %4 } define arm_aapcs_vfpcc <2 x i64> @test_vmlal_laneu32(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %arg2_uint32x2_t) nounwind readnone { @@ -180,14 +207,9 @@ entry: ; CHECK: test_vmlal_laneu32 ; CHECK: vmlal.u32 q0, d2, d3[1] %0 = shufflevector <2 x i32> %arg2_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1] - %1 = tail call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1] - ret <2 x i64> %1 + %1 = zext <2 x i32> %arg1_uint32x2_t to <2 x i64> + %2 = zext <2 x i32> %0 to <2 x i64> + %3 = mul <2 x i64> %1, %2 + %4 = add <2 x i64> %arg0_uint64x2_t, %3 + ret <2 x i64> %4 } - -declare <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone diff --git a/test/CodeGen/ARM/vmls.ll b/test/CodeGen/ARM/vmls.ll index 2b70a7878ced5..65e7fe41bb3a2 100644 --- a/test/CodeGen/ARM/vmls.ll +++ b/test/CodeGen/ARM/vmls.ll @@ -94,8 +94,11 @@ define <8 x i16> @vmlsls8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vmlsls.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = sext <8 x i8> %tmp3 to <8 x i16> + %tmp6 = mul <8 x i16> %tmp4, %tmp5 + %tmp7 = sub <8 x i16> %tmp1, %tmp6 + ret <8 x i16> %tmp7 } define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -104,8 +107,11 @@ define <4 x i32> @vmlsls16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vmlsls.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = sext <4 x i16> %tmp3 to <4 x i32> + %tmp6 = mul <4 x i32> %tmp4, %tmp5 + %tmp7 = sub <4 x i32> %tmp1, %tmp6 + ret <4 x i32> %tmp7 } define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -114,8 +120,11 @@ define <2 x i64> @vmlsls32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i64> @llvm.arm.neon.vmlsls.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i64> %tmp4 + %tmp4 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = sext <2 x i32> %tmp3 to <2 x i64> + %tmp6 = mul <2 x i64> %tmp4, %tmp5 + %tmp7 = sub <2 x i64> %tmp1, %tmp6 + ret <2 x i64> %tmp7 } define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { @@ -124,8 +133,11 @@ define <8 x i16> @vmlslu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind { %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B %tmp3 = load <8 x i8>* %C - %tmp4 = call <8 x i16> @llvm.arm.neon.vmlslu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3) - ret <8 x i16> %tmp4 + %tmp4 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = zext <8 x i8> %tmp3 to <8 x i16> + %tmp6 = mul <8 x i16> %tmp4, %tmp5 + %tmp7 = sub <8 x i16> %tmp1, %tmp6 + ret <8 x i16> %tmp7 } define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind { @@ -134,8 +146,11 @@ define <4 x i32> @vmlslu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B %tmp3 = load <4 x i16>* %C - %tmp4 = call <4 x i32> @llvm.arm.neon.vmlslu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3) - ret <4 x i32> %tmp4 + %tmp4 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = zext <4 x i16> %tmp3 to <4 x i32> + %tmp6 = mul <4 x i32> %tmp4, %tmp5 + %tmp7 = sub <4 x i32> %tmp1, %tmp6 + ret <4 x i32> %tmp7 } define <2 x i64> @vmlslu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind { @@ -144,8 +159,11 @@ define <2 x i64> @vmlslu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B %tmp3 = load <2 x i32>* %C - %tmp4 = call <2 x i64> @llvm.arm.neon.vmlslu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3) - ret <2 x i64> %tmp4 + %tmp4 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = zext <2 x i32> %tmp3 to <2 x i64> + %tmp6 = mul <2 x i64> %tmp4, %tmp5 + %tmp7 = sub <2 x i64> %tmp1, %tmp6 + ret <2 x i64> %tmp7 } define arm_aapcs_vfpcc <4 x i32> @test_vmlsl_lanes16(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %arg2_int16x4_t) nounwind readnone { @@ -153,8 +171,11 @@ entry: ; CHECK: test_vmlsl_lanes16 ; CHECK: vmlsl.s16 q0, d2, d3[1] %0 = shufflevector <4 x i16> %arg2_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1] - %1 = tail call <4 x i32> @llvm.arm.neon.vmlsls.v4i32(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1] - ret <4 x i32> %1 + %1 = sext <4 x i16> %arg1_int16x4_t to <4 x i32> + %2 = sext <4 x i16> %0 to <4 x i32> + %3 = mul <4 x i32> %1, %2 + %4 = sub <4 x i32> %arg0_int32x4_t, %3 + ret <4 x i32> %4 } define arm_aapcs_vfpcc <2 x i64> @test_vmlsl_lanes32(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %arg2_int32x2_t) nounwind readnone { @@ -162,8 +183,11 @@ entry: ; CHECK: test_vmlsl_lanes32 ; CHECK: vmlsl.s32 q0, d2, d3[1] %0 = shufflevector <2 x i32> %arg2_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1] - %1 = tail call <2 x i64> @llvm.arm.neon.vmlsls.v2i64(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1] - ret <2 x i64> %1 + %1 = sext <2 x i32> %arg1_int32x2_t to <2 x i64> + %2 = sext <2 x i32> %0 to <2 x i64> + %3 = mul <2 x i64> %1, %2 + %4 = sub <2 x i64> %arg0_int64x2_t, %3 + ret <2 x i64> %4 } define arm_aapcs_vfpcc <4 x i32> @test_vmlsl_laneu16(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %arg2_uint16x4_t) nounwind readnone { @@ -171,8 +195,11 @@ entry: ; CHECK: test_vmlsl_laneu16 ; CHECK: vmlsl.u16 q0, d2, d3[1] %0 = shufflevector <4 x i16> %arg2_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1] - %1 = tail call <4 x i32> @llvm.arm.neon.vmlslu.v4i32(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1] - ret <4 x i32> %1 + %1 = zext <4 x i16> %arg1_uint16x4_t to <4 x i32> + %2 = zext <4 x i16> %0 to <4 x i32> + %3 = mul <4 x i32> %1, %2 + %4 = sub <4 x i32> %arg0_uint32x4_t, %3 + ret <4 x i32> %4 } define arm_aapcs_vfpcc <2 x i64> @test_vmlsl_laneu32(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %arg2_uint32x2_t) nounwind readnone { @@ -180,14 +207,9 @@ entry: ; CHECK: test_vmlsl_laneu32 ; CHECK: vmlsl.u32 q0, d2, d3[1] %0 = shufflevector <2 x i32> %arg2_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1] - %1 = tail call <2 x i64> @llvm.arm.neon.vmlslu.v2i64(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1] - ret <2 x i64> %1 + %1 = zext <2 x i32> %arg1_uint32x2_t to <2 x i64> + %2 = zext <2 x i32> %0 to <2 x i64> + %3 = mul <2 x i64> %1, %2 + %4 = sub <2 x i64> %arg0_uint64x2_t, %3 + ret <2 x i64> %4 } - -declare <8 x i16> @llvm.arm.neon.vmlsls.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmlsls.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmlsls.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vmlslu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmlslu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmlslu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone diff --git a/test/CodeGen/ARM/vmov.ll b/test/CodeGen/ARM/vmov.ll index 5e872ab6d0b25..8cd94576b0c21 100644 --- a/test/CodeGen/ARM/vmov.ll +++ b/test/CodeGen/ARM/vmov.ll @@ -192,7 +192,7 @@ define <8 x i16> @vmovls8(<8 x i8>* %A) nounwind { ;CHECK: vmovls8: ;CHECK: vmovl.s8 %tmp1 = load <8 x i8>* %A - %tmp2 = call <8 x i16> @llvm.arm.neon.vmovls.v8i16(<8 x i8> %tmp1) + %tmp2 = sext <8 x i8> %tmp1 to <8 x i16> ret <8 x i16> %tmp2 } @@ -200,7 +200,7 @@ define <4 x i32> @vmovls16(<4 x i16>* %A) nounwind { ;CHECK: vmovls16: ;CHECK: vmovl.s16 %tmp1 = load <4 x i16>* %A - %tmp2 = call <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16> %tmp1) + %tmp2 = sext <4 x i16> %tmp1 to <4 x i32> ret <4 x i32> %tmp2 } @@ -208,7 +208,7 @@ define <2 x i64> @vmovls32(<2 x i32>* %A) nounwind { ;CHECK: vmovls32: ;CHECK: vmovl.s32 %tmp1 = load <2 x i32>* %A - %tmp2 = call <2 x i64> @llvm.arm.neon.vmovls.v2i64(<2 x i32> %tmp1) + %tmp2 = sext <2 x i32> %tmp1 to <2 x i64> ret <2 x i64> %tmp2 } @@ -216,7 +216,7 @@ define <8 x i16> @vmovlu8(<8 x i8>* %A) nounwind { ;CHECK: vmovlu8: ;CHECK: vmovl.u8 %tmp1 = load <8 x i8>* %A - %tmp2 = call <8 x i16> @llvm.arm.neon.vmovlu.v8i16(<8 x i8> %tmp1) + %tmp2 = zext <8 x i8> %tmp1 to <8 x i16> ret <8 x i16> %tmp2 } @@ -224,7 +224,7 @@ define <4 x i32> @vmovlu16(<4 x i16>* %A) nounwind { ;CHECK: vmovlu16: ;CHECK: vmovl.u16 %tmp1 = load <4 x i16>* %A - %tmp2 = call <4 x i32> @llvm.arm.neon.vmovlu.v4i32(<4 x i16> %tmp1) + %tmp2 = zext <4 x i16> %tmp1 to <4 x i32> ret <4 x i32> %tmp2 } @@ -232,23 +232,15 @@ define <2 x i64> @vmovlu32(<2 x i32>* %A) nounwind { ;CHECK: vmovlu32: ;CHECK: vmovl.u32 %tmp1 = load <2 x i32>* %A - %tmp2 = call <2 x i64> @llvm.arm.neon.vmovlu.v2i64(<2 x i32> %tmp1) + %tmp2 = zext <2 x i32> %tmp1 to <2 x i64> ret <2 x i64> %tmp2 } -declare <8 x i16> @llvm.arm.neon.vmovls.v8i16(<8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmovls.v4i32(<4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmovls.v2i64(<2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vmovlu.v8i16(<8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmovlu.v4i32(<4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmovlu.v2i64(<2 x i32>) nounwind readnone - define <8 x i8> @vmovni16(<8 x i16>* %A) nounwind { ;CHECK: vmovni16: ;CHECK: vmovn.i16 %tmp1 = load <8 x i16>* %A - %tmp2 = call <8 x i8> @llvm.arm.neon.vmovn.v8i8(<8 x i16> %tmp1) + %tmp2 = trunc <8 x i16> %tmp1 to <8 x i8> ret <8 x i8> %tmp2 } @@ -256,7 +248,7 @@ define <4 x i16> @vmovni32(<4 x i32>* %A) nounwind { ;CHECK: vmovni32: ;CHECK: vmovn.i32 %tmp1 = load <4 x i32>* %A - %tmp2 = call <4 x i16> @llvm.arm.neon.vmovn.v4i16(<4 x i32> %tmp1) + %tmp2 = trunc <4 x i32> %tmp1 to <4 x i16> ret <4 x i16> %tmp2 } @@ -264,14 +256,10 @@ define <2 x i32> @vmovni64(<2 x i64>* %A) nounwind { ;CHECK: vmovni64: ;CHECK: vmovn.i64 %tmp1 = load <2 x i64>* %A - %tmp2 = call <2 x i32> @llvm.arm.neon.vmovn.v2i32(<2 x i64> %tmp1) + %tmp2 = trunc <2 x i64> %tmp1 to <2 x i32> ret <2 x i32> %tmp2 } -declare <8 x i8> @llvm.arm.neon.vmovn.v8i8(<8 x i16>) nounwind readnone -declare <4 x i16> @llvm.arm.neon.vmovn.v4i16(<4 x i32>) nounwind readnone -declare <2 x i32> @llvm.arm.neon.vmovn.v2i32(<2 x i64>) nounwind readnone - define <8 x i8> @vqmovns16(<8 x i16>* %A) nounwind { ;CHECK: vqmovns16: ;CHECK: vqmovn.s16 diff --git a/test/CodeGen/ARM/vmul.ll b/test/CodeGen/ARM/vmul.ll index 1d91680212794..5383425018f8e 100644 --- a/test/CodeGen/ARM/vmul.ll +++ b/test/CodeGen/ARM/vmul.ll @@ -152,8 +152,10 @@ define <8 x i16> @vmulls8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vmull.s8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vmulls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = sext <8 x i8> %tmp1 to <8 x i16> + %tmp4 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = mul <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vmulls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -161,8 +163,10 @@ define <4 x i32> @vmulls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vmull.s16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = sext <4 x i16> %tmp1 to <4 x i32> + %tmp4 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = mul <4 x i32> %tmp3, %tmp4 + ret <4 x i32> %tmp5 } define <2 x i64> @vmulls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -170,8 +174,10 @@ define <2 x i64> @vmulls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vmull.s32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = sext <2 x i32> %tmp1 to <2 x i64> + %tmp4 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = mul <2 x i64> %tmp3, %tmp4 + ret <2 x i64> %tmp5 } define <8 x i16> @vmullu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { @@ -179,8 +185,10 @@ define <8 x i16> @vmullu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vmull.u8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vmullu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = zext <8 x i8> %tmp1 to <8 x i16> + %tmp4 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = mul <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vmullu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -188,8 +196,10 @@ define <4 x i32> @vmullu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vmull.u16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = zext <4 x i16> %tmp1 to <4 x i32> + %tmp4 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = mul <4 x i32> %tmp3, %tmp4 + ret <4 x i32> %tmp5 } define <2 x i64> @vmullu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -197,8 +207,10 @@ define <2 x i64> @vmullu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vmull.u32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = zext <2 x i32> %tmp1 to <2 x i64> + %tmp4 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = mul <2 x i64> %tmp3, %tmp4 + ret <2 x i64> %tmp5 } define <8 x i16> @vmullp8(<8 x i8>* %A, <8 x i8>* %B) nounwind { @@ -215,8 +227,10 @@ entry: ; CHECK: test_vmull_lanes16 ; CHECK: vmull.s16 q0, d0, d1[1] %0 = shufflevector <4 x i16> %arg1_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1] - %1 = tail call <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16> %arg0_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1] - ret <4 x i32> %1 + %1 = sext <4 x i16> %arg0_int16x4_t to <4 x i32> + %2 = sext <4 x i16> %0 to <4 x i32> + %3 = mul <4 x i32> %1, %2 + ret <4 x i32> %3 } define arm_aapcs_vfpcc <2 x i64> @test_vmull_lanes32(<2 x i32> %arg0_int32x2_t, <2 x i32> %arg1_int32x2_t) nounwind readnone { @@ -224,8 +238,10 @@ entry: ; CHECK: test_vmull_lanes32 ; CHECK: vmull.s32 q0, d0, d1[1] %0 = shufflevector <2 x i32> %arg1_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1] - %1 = tail call <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32> %arg0_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1] - ret <2 x i64> %1 + %1 = sext <2 x i32> %arg0_int32x2_t to <2 x i64> + %2 = sext <2 x i32> %0 to <2 x i64> + %3 = mul <2 x i64> %1, %2 + ret <2 x i64> %3 } define arm_aapcs_vfpcc <4 x i32> @test_vmull_laneu16(<4 x i16> %arg0_uint16x4_t, <4 x i16> %arg1_uint16x4_t) nounwind readnone { @@ -233,8 +249,10 @@ entry: ; CHECK: test_vmull_laneu16 ; CHECK: vmull.u16 q0, d0, d1[1] %0 = shufflevector <4 x i16> %arg1_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1] - %1 = tail call <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16> %arg0_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1] - ret <4 x i32> %1 + %1 = zext <4 x i16> %arg0_uint16x4_t to <4 x i32> + %2 = zext <4 x i16> %0 to <4 x i32> + %3 = mul <4 x i32> %1, %2 + ret <4 x i32> %3 } define arm_aapcs_vfpcc <2 x i64> @test_vmull_laneu32(<2 x i32> %arg0_uint32x2_t, <2 x i32> %arg1_uint32x2_t) nounwind readnone { @@ -242,16 +260,10 @@ entry: ; CHECK: test_vmull_laneu32 ; CHECK: vmull.u32 q0, d0, d1[1] %0 = shufflevector <2 x i32> %arg1_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1] - %1 = tail call <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32> %arg0_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1] - ret <2 x i64> %1 + %1 = zext <2 x i32> %arg0_uint32x2_t to <2 x i64> + %2 = zext <2 x i32> %0 to <2 x i64> + %3 = mul <2 x i64> %1, %2 + ret <2 x i64> %3 } -declare <8 x i16> @llvm.arm.neon.vmulls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmulls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmulls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vmullu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vmullu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vmullu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - declare <8 x i16> @llvm.arm.neon.vmullp.v8i16(<8 x i8>, <8 x i8>) nounwind readnone diff --git a/test/CodeGen/ARM/vrev.ll b/test/CodeGen/ARM/vrev.ll index deed554d842c6..e1fe64b02d9d3 100644 --- a/test/CodeGen/ARM/vrev.ll +++ b/test/CodeGen/ARM/vrev.ll @@ -111,3 +111,21 @@ define <16 x i8> @test_vrev16Q8(<16 x i8>* %A) nounwind { %tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14> ret <16 x i8> %tmp2 } + +; Undef shuffle indices should not prevent matching to VREV: + +define <8 x i8> @test_vrev64D8_undef(<8 x i8>* %A) nounwind { +;CHECK: test_vrev64D8_undef: +;CHECK: vrev64.8 + %tmp1 = load <8 x i8>* %A + %tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 undef, i32 undef, i32 4, i32 3, i32 2, i32 1, i32 0> + ret <8 x i8> %tmp2 +} + +define <8 x i16> @test_vrev32Q16_undef(<8 x i16>* %A) nounwind { +;CHECK: test_vrev32Q16_undef: +;CHECK: vrev32.16 + %tmp1 = load <8 x i16>* %A + %tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 undef, i32 0, i32 undef, i32 2, i32 5, i32 4, i32 7, i32 undef> + ret <8 x i16> %tmp2 +} diff --git a/test/CodeGen/ARM/vst1.ll b/test/CodeGen/ARM/vst1.ll index 95414c3089141..2b535ada30728 100644 --- a/test/CodeGen/ARM/vst1.ll +++ b/test/CodeGen/ARM/vst1.ll @@ -4,7 +4,7 @@ define void @vst1i8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst1i8: ;CHECK: vst1.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst1.v8i8(i8* %A, <8 x i8> %tmp1) + call void @llvm.arm.neon.vst1.v8i8(i8* %A, <8 x i8> %tmp1, i32 1) ret void } @@ -13,7 +13,7 @@ define void @vst1i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst1.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst1.v4i16(i8* %tmp0, <4 x i16> %tmp1) + call void @llvm.arm.neon.vst1.v4i16(i8* %tmp0, <4 x i16> %tmp1, i32 1) ret void } @@ -22,7 +22,7 @@ define void @vst1i32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst1.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst1.v2i32(i8* %tmp0, <2 x i32> %tmp1) + call void @llvm.arm.neon.vst1.v2i32(i8* %tmp0, <2 x i32> %tmp1, i32 1) ret void } @@ -31,7 +31,7 @@ define void @vst1f(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst1.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst1.v2f32(i8* %tmp0, <2 x float> %tmp1) + call void @llvm.arm.neon.vst1.v2f32(i8* %tmp0, <2 x float> %tmp1, i32 1) ret void } @@ -40,7 +40,7 @@ define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind { ;CHECK: vst1.64 %tmp0 = bitcast i64* %A to i8* %tmp1 = load <1 x i64>* %B - call void @llvm.arm.neon.vst1.v1i64(i8* %tmp0, <1 x i64> %tmp1) + call void @llvm.arm.neon.vst1.v1i64(i8* %tmp0, <1 x i64> %tmp1, i32 1) ret void } @@ -48,7 +48,7 @@ define void @vst1Qi8(i8* %A, <16 x i8>* %B) nounwind { ;CHECK: vst1Qi8: ;CHECK: vst1.8 %tmp1 = load <16 x i8>* %B - call void @llvm.arm.neon.vst1.v16i8(i8* %A, <16 x i8> %tmp1) + call void @llvm.arm.neon.vst1.v16i8(i8* %A, <16 x i8> %tmp1, i32 1) ret void } @@ -57,7 +57,7 @@ define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst1.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst1.v8i16(i8* %tmp0, <8 x i16> %tmp1) + call void @llvm.arm.neon.vst1.v8i16(i8* %tmp0, <8 x i16> %tmp1, i32 1) ret void } @@ -66,7 +66,7 @@ define void @vst1Qi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst1.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst1.v4i32(i8* %tmp0, <4 x i32> %tmp1) + call void @llvm.arm.neon.vst1.v4i32(i8* %tmp0, <4 x i32> %tmp1, i32 1) ret void } @@ -75,7 +75,7 @@ define void @vst1Qf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst1.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst1.v4f32(i8* %tmp0, <4 x float> %tmp1) + call void @llvm.arm.neon.vst1.v4f32(i8* %tmp0, <4 x float> %tmp1, i32 1) ret void } @@ -84,18 +84,18 @@ define void @vst1Qi64(i64* %A, <2 x i64>* %B) nounwind { ;CHECK: vst1.64 %tmp0 = bitcast i64* %A to i8* %tmp1 = load <2 x i64>* %B - call void @llvm.arm.neon.vst1.v2i64(i8* %tmp0, <2 x i64> %tmp1) + call void @llvm.arm.neon.vst1.v2i64(i8* %tmp0, <2 x i64> %tmp1, i32 1) ret void } -declare void @llvm.arm.neon.vst1.v8i8(i8*, <8 x i8>) nounwind -declare void @llvm.arm.neon.vst1.v4i16(i8*, <4 x i16>) nounwind -declare void @llvm.arm.neon.vst1.v2i32(i8*, <2 x i32>) nounwind -declare void @llvm.arm.neon.vst1.v2f32(i8*, <2 x float>) nounwind -declare void @llvm.arm.neon.vst1.v1i64(i8*, <1 x i64>) nounwind +declare void @llvm.arm.neon.vst1.v8i8(i8*, <8 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst1.v4i16(i8*, <4 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst1.v2i32(i8*, <2 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst1.v2f32(i8*, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst1.v1i64(i8*, <1 x i64>, i32) nounwind -declare void @llvm.arm.neon.vst1.v16i8(i8*, <16 x i8>) nounwind -declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>) nounwind -declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>) nounwind -declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>) nounwind -declare void @llvm.arm.neon.vst1.v2i64(i8*, <2 x i64>) nounwind +declare void @llvm.arm.neon.vst1.v16i8(i8*, <16 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst1.v8i16(i8*, <8 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst1.v4i32(i8*, <4 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst1.v4f32(i8*, <4 x float>, i32) nounwind +declare void @llvm.arm.neon.vst1.v2i64(i8*, <2 x i64>, i32) nounwind diff --git a/test/CodeGen/ARM/vst2.ll b/test/CodeGen/ARM/vst2.ll index 3c98a2cbe60dd..aed15fd51c56b 100644 --- a/test/CodeGen/ARM/vst2.ll +++ b/test/CodeGen/ARM/vst2.ll @@ -4,7 +4,7 @@ define void @vst2i8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst2i8: ;CHECK: vst2.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst2.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1) + call void @llvm.arm.neon.vst2.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) ret void } @@ -13,7 +13,7 @@ define void @vst2i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst2.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst2.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1) + call void @llvm.arm.neon.vst2.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) ret void } @@ -22,7 +22,7 @@ define void @vst2i32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst2.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1) + call void @llvm.arm.neon.vst2.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) ret void } @@ -31,7 +31,7 @@ define void @vst2f(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst2.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1) + call void @llvm.arm.neon.vst2.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) ret void } @@ -40,7 +40,7 @@ define void @vst2i64(i64* %A, <1 x i64>* %B) nounwind { ;CHECK: vst1.64 %tmp0 = bitcast i64* %A to i8* %tmp1 = load <1 x i64>* %B - call void @llvm.arm.neon.vst2.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1) + call void @llvm.arm.neon.vst2.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 1) ret void } @@ -48,7 +48,7 @@ define void @vst2Qi8(i8* %A, <16 x i8>* %B) nounwind { ;CHECK: vst2Qi8: ;CHECK: vst2.8 %tmp1 = load <16 x i8>* %B - call void @llvm.arm.neon.vst2.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1) + call void @llvm.arm.neon.vst2.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 1) ret void } @@ -57,7 +57,7 @@ define void @vst2Qi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst2.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst2.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1) + call void @llvm.arm.neon.vst2.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) ret void } @@ -66,7 +66,7 @@ define void @vst2Qi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst2.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1) + call void @llvm.arm.neon.vst2.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1) ret void } @@ -75,17 +75,17 @@ define void @vst2Qf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst2.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1) + call void @llvm.arm.neon.vst2.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) ret void } -declare void @llvm.arm.neon.vst2.v8i8(i8*, <8 x i8>, <8 x i8>) nounwind -declare void @llvm.arm.neon.vst2.v4i16(i8*, <4 x i16>, <4 x i16>) nounwind -declare void @llvm.arm.neon.vst2.v2i32(i8*, <2 x i32>, <2 x i32>) nounwind -declare void @llvm.arm.neon.vst2.v2f32(i8*, <2 x float>, <2 x float>) nounwind -declare void @llvm.arm.neon.vst2.v1i64(i8*, <1 x i64>, <1 x i64>) nounwind +declare void @llvm.arm.neon.vst2.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst2.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst2.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst2.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst2.v1i64(i8*, <1 x i64>, <1 x i64>, i32) nounwind -declare void @llvm.arm.neon.vst2.v16i8(i8*, <16 x i8>, <16 x i8>) nounwind -declare void @llvm.arm.neon.vst2.v8i16(i8*, <8 x i16>, <8 x i16>) nounwind -declare void @llvm.arm.neon.vst2.v4i32(i8*, <4 x i32>, <4 x i32>) nounwind -declare void @llvm.arm.neon.vst2.v4f32(i8*, <4 x float>, <4 x float>) nounwind +declare void @llvm.arm.neon.vst2.v16i8(i8*, <16 x i8>, <16 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst2.v8i16(i8*, <8 x i16>, <8 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst2.v4i32(i8*, <4 x i32>, <4 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst2.v4f32(i8*, <4 x float>, <4 x float>, i32) nounwind diff --git a/test/CodeGen/ARM/vst3.ll b/test/CodeGen/ARM/vst3.ll index 2599bc0db933b..1feaed5a10445 100644 --- a/test/CodeGen/ARM/vst3.ll +++ b/test/CodeGen/ARM/vst3.ll @@ -1,10 +1,10 @@ -; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s +; RUN: llc < %s -march=arm -mattr=+neon -O0 | FileCheck %s define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst3i8: ;CHECK: vst3.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1) + call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) ret void } @@ -13,7 +13,7 @@ define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst3.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1) + call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) ret void } @@ -22,7 +22,7 @@ define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1) + call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) ret void } @@ -31,7 +31,7 @@ define void @vst3f(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1) + call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) ret void } @@ -40,7 +40,7 @@ define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind { ;CHECK: vst1.64 %tmp0 = bitcast i64* %A to i8* %tmp1 = load <1 x i64>* %B - call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1) + call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 1) ret void } @@ -49,7 +49,7 @@ define void @vst3Qi8(i8* %A, <16 x i8>* %B) nounwind { ;CHECK: vst3.8 ;CHECK: vst3.8 %tmp1 = load <16 x i8>* %B - call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1) + call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 1) ret void } @@ -59,7 +59,7 @@ define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst3.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1) + call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) ret void } @@ -69,7 +69,7 @@ define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1) + call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1) ret void } @@ -79,17 +79,17 @@ define void @vst3Qf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1) + call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) ret void } -declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind -declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>) nounwind -declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>) nounwind -declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>) nounwind -declare void @llvm.arm.neon.vst3.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>) nounwind +declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst3.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind -declare void @llvm.arm.neon.vst3.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>) nounwind -declare void @llvm.arm.neon.vst3.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>) nounwind -declare void @llvm.arm.neon.vst3.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>) nounwind -declare void @llvm.arm.neon.vst3.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>) nounwind +declare void @llvm.arm.neon.vst3.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst3.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst3.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst3.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll index 878f0efaa4807..d302f097fc1fd 100644 --- a/test/CodeGen/ARM/vst4.ll +++ b/test/CodeGen/ARM/vst4.ll @@ -4,7 +4,7 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst4i8: ;CHECK: vst4.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1) + call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) ret void } @@ -13,7 +13,7 @@ define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst4.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst4.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1) + call void @llvm.arm.neon.vst4.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) ret void } @@ -22,7 +22,7 @@ define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst4.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1) + call void @llvm.arm.neon.vst4.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) ret void } @@ -31,7 +31,7 @@ define void @vst4f(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst4.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1) + call void @llvm.arm.neon.vst4.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) ret void } @@ -40,7 +40,7 @@ define void @vst4i64(i64* %A, <1 x i64>* %B) nounwind { ;CHECK: vst1.64 %tmp0 = bitcast i64* %A to i8* %tmp1 = load <1 x i64>* %B - call void @llvm.arm.neon.vst4.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1) + call void @llvm.arm.neon.vst4.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 1) ret void } @@ -49,7 +49,7 @@ define void @vst4Qi8(i8* %A, <16 x i8>* %B) nounwind { ;CHECK: vst4.8 ;CHECK: vst4.8 %tmp1 = load <16 x i8>* %B - call void @llvm.arm.neon.vst4.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1) + call void @llvm.arm.neon.vst4.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 1) ret void } @@ -59,7 +59,7 @@ define void @vst4Qi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst4.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst4.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1) + call void @llvm.arm.neon.vst4.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) ret void } @@ -69,7 +69,7 @@ define void @vst4Qi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst4.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1) + call void @llvm.arm.neon.vst4.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1) ret void } @@ -79,17 +79,17 @@ define void @vst4Qf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst4.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1) + call void @llvm.arm.neon.vst4.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) ret void } -declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind -declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>) nounwind -declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>) nounwind -declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>) nounwind -declare void @llvm.arm.neon.vst4.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64>) nounwind +declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst4.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind -declare void @llvm.arm.neon.vst4.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind -declare void @llvm.arm.neon.vst4.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>) nounwind -declare void @llvm.arm.neon.vst4.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>) nounwind -declare void @llvm.arm.neon.vst4.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>) nounwind +declare void @llvm.arm.neon.vst4.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst4.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst4.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst4.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll index cf50756d465e5..30ec52ac64209 100644 --- a/test/CodeGen/ARM/vstlane.ll +++ b/test/CodeGen/ARM/vstlane.ll @@ -4,7 +4,7 @@ define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst2lanei8: ;CHECK: vst2.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) + call void @llvm.arm.neon.vst2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) ret void } @@ -13,7 +13,7 @@ define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst2.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) + call void @llvm.arm.neon.vst2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1) ret void } @@ -22,7 +22,7 @@ define void @vst2lanei32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) + call void @llvm.arm.neon.vst2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1) ret void } @@ -31,7 +31,7 @@ define void @vst2lanef(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) + call void @llvm.arm.neon.vst2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1) ret void } @@ -40,7 +40,7 @@ define void @vst2laneQi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst2.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) + call void @llvm.arm.neon.vst2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 1) ret void } @@ -49,7 +49,7 @@ define void @vst2laneQi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2) + call void @llvm.arm.neon.vst2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 1) ret void } @@ -58,24 +58,24 @@ define void @vst2laneQf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst2.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 3) + call void @llvm.arm.neon.vst2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 3, i32 1) ret void } -declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind -declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32, i32) nounwind -declare void @llvm.arm.neon.vst2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst2lane.v4f32(i8*, <4 x float>, <4 x float>, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32, i32) nounwind +declare void @llvm.arm.neon.vst2lane.v4f32(i8*, <4 x float>, <4 x float>, i32, i32) nounwind define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst3lanei8: ;CHECK: vst3.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) + call void @llvm.arm.neon.vst3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) ret void } @@ -84,7 +84,7 @@ define void @vst3lanei16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst3.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) + call void @llvm.arm.neon.vst3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1) ret void } @@ -93,7 +93,7 @@ define void @vst3lanei32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) + call void @llvm.arm.neon.vst3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1) ret void } @@ -102,7 +102,7 @@ define void @vst3lanef(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) + call void @llvm.arm.neon.vst3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1) ret void } @@ -111,7 +111,7 @@ define void @vst3laneQi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst3.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 6) + call void @llvm.arm.neon.vst3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 6, i32 1) ret void } @@ -120,7 +120,7 @@ define void @vst3laneQi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 0) + call void @llvm.arm.neon.vst3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 0, i32 1) ret void } @@ -129,25 +129,25 @@ define void @vst3laneQf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst3.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) + call void @llvm.arm.neon.vst3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1) ret void } -declare void @llvm.arm.neon.vst3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind -declare void @llvm.arm.neon.vst3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind -declare void @llvm.arm.neon.vst3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind +declare void @llvm.arm.neon.vst3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind { ;CHECK: vst4lanei8: ;CHECK: vst4.8 %tmp1 = load <8 x i8>* %B - call void @llvm.arm.neon.vst4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1) + call void @llvm.arm.neon.vst4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1) ret void } @@ -156,7 +156,7 @@ define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst4.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>* %B - call void @llvm.arm.neon.vst4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1) + call void @llvm.arm.neon.vst4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1) ret void } @@ -165,7 +165,7 @@ define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>* %B - call void @llvm.arm.neon.vst4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1) + call void @llvm.arm.neon.vst4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1) ret void } @@ -174,7 +174,7 @@ define void @vst4lanef(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>* %B - call void @llvm.arm.neon.vst4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) + call void @llvm.arm.neon.vst4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1) ret void } @@ -183,7 +183,7 @@ define void @vst4laneQi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst4.16 %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>* %B - call void @llvm.arm.neon.vst4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 7) + call void @llvm.arm.neon.vst4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 7, i32 1) ret void } @@ -192,7 +192,7 @@ define void @vst4laneQi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>* %B - call void @llvm.arm.neon.vst4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2) + call void @llvm.arm.neon.vst4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 1) ret void } @@ -201,15 +201,15 @@ define void @vst4laneQf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>* %B - call void @llvm.arm.neon.vst4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) + call void @llvm.arm.neon.vst4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1) ret void } -declare void @llvm.arm.neon.vst4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind -declare void @llvm.arm.neon.vst4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind -declare void @llvm.arm.neon.vst4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind +declare void @llvm.arm.neon.vst4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind diff --git a/test/CodeGen/ARM/vsub.ll b/test/CodeGen/ARM/vsub.ll index 3416de76f123e..df77bb31fc8b8 100644 --- a/test/CodeGen/ARM/vsub.ll +++ b/test/CodeGen/ARM/vsub.ll @@ -157,8 +157,10 @@ define <8 x i16> @vsubls8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vsubl.s8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vsubls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = sext <8 x i8> %tmp1 to <8 x i16> + %tmp4 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = sub <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vsubls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -166,8 +168,10 @@ define <4 x i32> @vsubls16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vsubl.s16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vsubls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = sext <4 x i16> %tmp1 to <4 x i32> + %tmp4 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = sub <4 x i32> %tmp3, %tmp4 + ret <4 x i32> %tmp5 } define <2 x i64> @vsubls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -175,8 +179,10 @@ define <2 x i64> @vsubls32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vsubl.s32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vsubls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = sext <2 x i32> %tmp1 to <2 x i64> + %tmp4 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = sub <2 x i64> %tmp3, %tmp4 + ret <2 x i64> %tmp5 } define <8 x i16> @vsublu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { @@ -184,8 +190,10 @@ define <8 x i16> @vsublu8(<8 x i8>* %A, <8 x i8>* %B) nounwind { ;CHECK: vsubl.u8 %tmp1 = load <8 x i8>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vsublu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = zext <8 x i8> %tmp1 to <8 x i16> + %tmp4 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp5 = sub <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 } define <4 x i32> @vsublu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { @@ -193,8 +201,10 @@ define <4 x i32> @vsublu16(<4 x i16>* %A, <4 x i16>* %B) nounwind { ;CHECK: vsubl.u16 %tmp1 = load <4 x i16>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vsublu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = zext <4 x i16> %tmp1 to <4 x i32> + %tmp4 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp5 = sub <4 x i32> %tmp3, %tmp4 + ret <4 x i32> %tmp5 } define <2 x i64> @vsublu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { @@ -202,25 +212,20 @@ define <2 x i64> @vsublu32(<2 x i32>* %A, <2 x i32>* %B) nounwind { ;CHECK: vsubl.u32 %tmp1 = load <2 x i32>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vsublu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = zext <2 x i32> %tmp1 to <2 x i64> + %tmp4 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp5 = sub <2 x i64> %tmp3, %tmp4 + ret <2 x i64> %tmp5 } -declare <8 x i16> @llvm.arm.neon.vsubls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vsubls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vsubls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vsublu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vsublu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vsublu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone - define <8 x i16> @vsubws8(<8 x i16>* %A, <8 x i8>* %B) nounwind { ;CHECK: vsubws8: ;CHECK: vsubw.s8 %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vsubws.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = sext <8 x i8> %tmp2 to <8 x i16> + %tmp4 = sub <8 x i16> %tmp1, %tmp3 + ret <8 x i16> %tmp4 } define <4 x i32> @vsubws16(<4 x i32>* %A, <4 x i16>* %B) nounwind { @@ -228,8 +233,9 @@ define <4 x i32> @vsubws16(<4 x i32>* %A, <4 x i16>* %B) nounwind { ;CHECK: vsubw.s16 %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vsubws.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = sext <4 x i16> %tmp2 to <4 x i32> + %tmp4 = sub <4 x i32> %tmp1, %tmp3 + ret <4 x i32> %tmp4 } define <2 x i64> @vsubws32(<2 x i64>* %A, <2 x i32>* %B) nounwind { @@ -237,8 +243,9 @@ define <2 x i64> @vsubws32(<2 x i64>* %A, <2 x i32>* %B) nounwind { ;CHECK: vsubw.s32 %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vsubws.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = sext <2 x i32> %tmp2 to <2 x i64> + %tmp4 = sub <2 x i64> %tmp1, %tmp3 + ret <2 x i64> %tmp4 } define <8 x i16> @vsubwu8(<8 x i16>* %A, <8 x i8>* %B) nounwind { @@ -246,8 +253,9 @@ define <8 x i16> @vsubwu8(<8 x i16>* %A, <8 x i8>* %B) nounwind { ;CHECK: vsubw.u8 %tmp1 = load <8 x i16>* %A %tmp2 = load <8 x i8>* %B - %tmp3 = call <8 x i16> @llvm.arm.neon.vsubwu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2) - ret <8 x i16> %tmp3 + %tmp3 = zext <8 x i8> %tmp2 to <8 x i16> + %tmp4 = sub <8 x i16> %tmp1, %tmp3 + ret <8 x i16> %tmp4 } define <4 x i32> @vsubwu16(<4 x i32>* %A, <4 x i16>* %B) nounwind { @@ -255,8 +263,9 @@ define <4 x i32> @vsubwu16(<4 x i32>* %A, <4 x i16>* %B) nounwind { ;CHECK: vsubw.u16 %tmp1 = load <4 x i32>* %A %tmp2 = load <4 x i16>* %B - %tmp3 = call <4 x i32> @llvm.arm.neon.vsubwu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2) - ret <4 x i32> %tmp3 + %tmp3 = zext <4 x i16> %tmp2 to <4 x i32> + %tmp4 = sub <4 x i32> %tmp1, %tmp3 + ret <4 x i32> %tmp4 } define <2 x i64> @vsubwu32(<2 x i64>* %A, <2 x i32>* %B) nounwind { @@ -264,14 +273,7 @@ define <2 x i64> @vsubwu32(<2 x i64>* %A, <2 x i32>* %B) nounwind { ;CHECK: vsubw.u32 %tmp1 = load <2 x i64>* %A %tmp2 = load <2 x i32>* %B - %tmp3 = call <2 x i64> @llvm.arm.neon.vsubwu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2) - ret <2 x i64> %tmp3 + %tmp3 = zext <2 x i32> %tmp2 to <2 x i64> + %tmp4 = sub <2 x i64> %tmp1, %tmp3 + ret <2 x i64> %tmp4 } - -declare <8 x i16> @llvm.arm.neon.vsubws.v8i16(<8 x i16>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vsubws.v4i32(<4 x i32>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vsubws.v2i64(<2 x i64>, <2 x i32>) nounwind readnone - -declare <8 x i16> @llvm.arm.neon.vsubwu.v8i16(<8 x i16>, <8 x i8>) nounwind readnone -declare <4 x i32> @llvm.arm.neon.vsubwu.v4i32(<4 x i32>, <4 x i16>) nounwind readnone -declare <2 x i64> @llvm.arm.neon.vsubwu.v2i64(<2 x i64>, <2 x i32>) nounwind readnone diff --git a/test/CodeGen/ARM/vtrn.ll b/test/CodeGen/ARM/vtrn.ll index 10bb10ac24a17..b1c2f93b47c6c 100644 --- a/test/CodeGen/ARM/vtrn.ll +++ b/test/CodeGen/ARM/vtrn.ll @@ -95,3 +95,30 @@ define <4 x float> @vtrnQf(<4 x float>* %A, <4 x float>* %B) nounwind { %tmp5 = fadd <4 x float> %tmp3, %tmp4 ret <4 x float> %tmp5 } + +; Undef shuffle indices should not prevent matching to VTRN: + +define <8 x i8> @vtrni8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind { +;CHECK: vtrni8_undef: +;CHECK: vtrn.8 +;CHECK-NEXT: vadd.i8 + %tmp1 = load <8 x i8>* %A + %tmp2 = load <8 x i8>* %B + %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 undef, i32 2, i32 10, i32 undef, i32 12, i32 6, i32 14> + %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 undef, i32 undef, i32 15> + %tmp5 = add <8 x i8> %tmp3, %tmp4 + ret <8 x i8> %tmp5 +} + +define <8 x i16> @vtrnQi16_undef(<8 x i16>* %A, <8 x i16>* %B) nounwind { +;CHECK: vtrnQi16_undef: +;CHECK: vtrn.16 +;CHECK-NEXT: vadd.i16 + %tmp1 = load <8 x i16>* %A + %tmp2 = load <8 x i16>* %B + %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 undef, i32 undef, i32 4, i32 12, i32 6, i32 14> + %tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 undef, i32 3, i32 11, i32 5, i32 13, i32 undef, i32 undef> + %tmp5 = add <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 +} + diff --git a/test/CodeGen/ARM/vuzp.ll b/test/CodeGen/ARM/vuzp.ll index 6cef188d76dd4..9130f628919a5 100644 --- a/test/CodeGen/ARM/vuzp.ll +++ b/test/CodeGen/ARM/vuzp.ll @@ -73,3 +73,30 @@ define <4 x float> @vuzpQf(<4 x float>* %A, <4 x float>* %B) nounwind { %tmp5 = fadd <4 x float> %tmp3, %tmp4 ret <4 x float> %tmp5 } + +; Undef shuffle indices should not prevent matching to VUZP: + +define <8 x i8> @vuzpi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind { +;CHECK: vuzpi8_undef: +;CHECK: vuzp.8 +;CHECK-NEXT: vadd.i8 + %tmp1 = load <8 x i8>* %A + %tmp2 = load <8 x i8>* %B + %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 8, i32 10, i32 12, i32 14> + %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 13, i32 15> + %tmp5 = add <8 x i8> %tmp3, %tmp4 + ret <8 x i8> %tmp5 +} + +define <8 x i16> @vuzpQi16_undef(<8 x i16>* %A, <8 x i16>* %B) nounwind { +;CHECK: vuzpQi16_undef: +;CHECK: vuzp.16 +;CHECK-NEXT: vadd.i16 + %tmp1 = load <8 x i16>* %A + %tmp2 = load <8 x i16>* %B + %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 14> + %tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 undef, i32 undef, i32 11, i32 13, i32 15> + %tmp5 = add <8 x i16> %tmp3, %tmp4 + ret <8 x i16> %tmp5 +} + diff --git a/test/CodeGen/ARM/vzip.ll b/test/CodeGen/ARM/vzip.ll index a9ecdcab42d7e..926970aeb29b4 100644 --- a/test/CodeGen/ARM/vzip.ll +++ b/test/CodeGen/ARM/vzip.ll @@ -73,3 +73,30 @@ define <4 x float> @vzipQf(<4 x float>* %A, <4 x float>* %B) nounwind { %tmp5 = fadd <4 x float> %tmp3, %tmp4 ret <4 x float> %tmp5 } + +; Undef shuffle indices should not prevent matching to VZIP: + +define <8 x i8> @vzipi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind { +;CHECK: vzipi8_undef: +;CHECK: vzip.8 +;CHECK-NEXT: vadd.i8 + %tmp1 = load <8 x i8>* %A + %tmp2 = load <8 x i8>* %B + %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11> + %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15> + %tmp5 = add <8 x i8> %tmp3, %tmp4 + ret <8 x i8> %tmp5 +} + +define <16 x i8> @vzipQi8_undef(<16 x i8>* %A, <16 x i8>* %B) nounwind { +;CHECK: vzipQi8_undef: +;CHECK: vzip.8 +;CHECK-NEXT: vadd.i8 + %tmp1 = load <16 x i8>* %A + %tmp2 = load <16 x i8>* %B + %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23> + %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31> + %tmp5 = add <16 x i8> %tmp3, %tmp4 + ret <16 x i8> %tmp5 +} + |