diff options
Diffstat (limited to 'test/CodeGen/X86/widen_arith-1.ll')
-rw-r--r-- | test/CodeGen/X86/widen_arith-1.ll | 76 |
1 files changed, 51 insertions, 25 deletions
diff --git a/test/CodeGen/X86/widen_arith-1.ll b/test/CodeGen/X86/widen_arith-1.ll index 5663b8b40946c..a1e9b53638c6e 100644 --- a/test/CodeGen/X86/widen_arith-1.ll +++ b/test/CodeGen/X86/widen_arith-1.ll @@ -1,44 +1,70 @@ -; RUN: llc < %s -mcpu=generic -march=x86 -mattr=+sse4.2 | FileCheck %s +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.2 | FileCheck %s define void @update(<3 x i8>* %dst, <3 x i8>* %src, i32 %n) nounwind { +; CHECK-LABEL: update: +; CHECK: # BB#0: # %entry +; CHECK-NEXT: subl $12, %esp +; CHECK-NEXT: movl $0, (%esp) +; CHECK-NEXT: pcmpeqd %xmm0, %xmm0 +; CHECK-NEXT: movdqa {{.*#+}} xmm1 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u> +; CHECK-NEXT: jmp .LBB0_1 +; CHECK-NEXT: .p2align 4, 0x90 +; CHECK-NEXT: .LBB0_2: # %forbody +; CHECK-NEXT: # in Loop: Header=BB0_1 Depth=1 +; CHECK-NEXT: movl (%esp), %eax +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %edx +; CHECK-NEXT: pmovzxbd {{.*#+}} xmm2 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero +; CHECK-NEXT: psubd %xmm0, %xmm2 +; CHECK-NEXT: pextrb $8, %xmm2, 2(%ecx,%eax,4) +; CHECK-NEXT: pshufb %xmm1, %xmm2 +; CHECK-NEXT: pextrw $0, %xmm2, (%ecx,%eax,4) +; CHECK-NEXT: incl (%esp) +; CHECK-NEXT: .LBB0_1: # %forcond +; CHECK-NEXT: # =>This Inner Loop Header: Depth=1 +; CHECK-NEXT: movl (%esp), %eax +; CHECK-NEXT: cmpl {{[0-9]+}}(%esp), %eax +; CHECK-NEXT: jl .LBB0_2 +; CHECK-NEXT: # BB#3: # %afterfor +; CHECK-NEXT: addl $12, %esp +; CHECK-NEXT: retl entry: -; CHECK-NOT: pextrw -; CHECK: add - - %dst.addr = alloca <3 x i8>* ; <<3 x i8>**> [#uses=2] - %src.addr = alloca <3 x i8>* ; <<3 x i8>**> [#uses=2] - %n.addr = alloca i32 ; <i32*> [#uses=2] - %i = alloca i32, align 4 ; <i32*> [#uses=6] + %dst.addr = alloca <3 x i8>* + %src.addr = alloca <3 x i8>* + %n.addr = alloca i32 + %i = alloca i32, align 4 store <3 x i8>* %dst, <3 x i8>** %dst.addr store <3 x i8>* %src, <3 x i8>** %src.addr store i32 %n, i32* %n.addr store i32 0, i32* %i br label %forcond -forcond: ; preds = %forinc, %entry - %tmp = load i32, i32* %i ; <i32> [#uses=1] - %tmp1 = load i32, i32* %n.addr ; <i32> [#uses=1] - %cmp = icmp slt i32 %tmp, %tmp1 ; <i1> [#uses=1] +forcond: + %tmp = load i32, i32* %i + %tmp1 = load i32, i32* %n.addr + %cmp = icmp slt i32 %tmp, %tmp1 br i1 %cmp, label %forbody, label %afterfor -forbody: ; preds = %forcond - %tmp2 = load i32, i32* %i ; <i32> [#uses=1] - %tmp3 = load <3 x i8>*, <3 x i8>** %dst.addr ; <<3 x i8>*> [#uses=1] - %arrayidx = getelementptr <3 x i8>, <3 x i8>* %tmp3, i32 %tmp2 ; <<3 x i8>*> [#uses=1] - %tmp4 = load i32, i32* %i ; <i32> [#uses=1] - %tmp5 = load <3 x i8>*, <3 x i8>** %src.addr ; <<3 x i8>*> [#uses=1] - %arrayidx6 = getelementptr <3 x i8>, <3 x i8>* %tmp5, i32 %tmp4 ; <<3 x i8>*> [#uses=1] - %tmp7 = load <3 x i8>, <3 x i8>* %arrayidx6 ; <<3 x i8>> [#uses=1] - %add = add <3 x i8> %tmp7, < i8 1, i8 1, i8 1 > ; <<3 x i8>> [#uses=1] +forbody: + %tmp2 = load i32, i32* %i + %tmp3 = load <3 x i8>*, <3 x i8>** %dst.addr + %arrayidx = getelementptr <3 x i8>, <3 x i8>* %tmp3, i32 %tmp2 + %tmp4 = load i32, i32* %i + %tmp5 = load <3 x i8>*, <3 x i8>** %src.addr + %arrayidx6 = getelementptr <3 x i8>, <3 x i8>* %tmp5, i32 %tmp4 + %tmp7 = load <3 x i8>, <3 x i8>* %arrayidx6 + %add = add <3 x i8> %tmp7, < i8 1, i8 1, i8 1 > store <3 x i8> %add, <3 x i8>* %arrayidx br label %forinc -forinc: ; preds = %forbody - %tmp8 = load i32, i32* %i ; <i32> [#uses=1] - %inc = add i32 %tmp8, 1 ; <i32> [#uses=1] +forinc: + %tmp8 = load i32, i32* %i + %inc = add i32 %tmp8, 1 store i32 %inc, i32* %i br label %forcond -afterfor: ; preds = %forcond +afterfor: ret void } + |