aboutsummaryrefslogtreecommitdiff
path: root/test/CodeGen/X86
diff options
context:
space:
mode:
authorRoman Divacky <rdivacky@FreeBSD.org>2010-04-02 08:54:30 +0000
committerRoman Divacky <rdivacky@FreeBSD.org>2010-04-02 08:54:30 +0000
commit104bd8179fb5f6551c65c94ebcd0a4918b060189 (patch)
treecf5763d092b81cecc168fa28032247ee495d06e2 /test/CodeGen/X86
parent2f12f10af369d468b14617276446166383d692ed (diff)
Notes
Diffstat (limited to 'test/CodeGen/X86')
-rw-r--r--test/CodeGen/X86/2007-01-13-StackPtrIndex.ll1
-rw-r--r--test/CodeGen/X86/2007-04-25-MMX-PADDQ.ll10
-rw-r--r--test/CodeGen/X86/2009-02-05-CoalescerBug.ll6
-rw-r--r--test/CodeGen/X86/2009-02-26-MachineLICMBug.ll11
-rw-r--r--test/CodeGen/X86/2009-11-16-UnfoldMemOpBug.ll2
-rw-r--r--test/CodeGen/X86/byval7.ll9
-rw-r--r--test/CodeGen/X86/coalesce-esp.ll2
-rw-r--r--test/CodeGen/X86/dagcombine-buildvector.ll10
-rw-r--r--test/CodeGen/X86/gather-addresses.ll2
-rw-r--r--test/CodeGen/X86/licm-symbol.ll2
-rw-r--r--test/CodeGen/X86/memcpy-2.ll117
-rw-r--r--test/CodeGen/X86/memset-2.ll52
-rw-r--r--test/CodeGen/X86/memset64-on-x86-32.ll5
-rw-r--r--test/CodeGen/X86/pic.ll8
-rw-r--r--test/CodeGen/X86/pmul.ll2
-rw-r--r--test/CodeGen/X86/pmulld.ll16
-rw-r--r--test/CodeGen/X86/postalloc-coalescing.ll2
-rw-r--r--test/CodeGen/X86/pr2659.ll6
-rw-r--r--test/CodeGen/X86/sibcall.ll42
-rw-r--r--test/CodeGen/X86/small-byval-memcpy.ll6
-rw-r--r--test/CodeGen/X86/sse-align-12.ll22
-rw-r--r--test/CodeGen/X86/sse-align-6.ll2
-rw-r--r--test/CodeGen/X86/sse3.ll8
-rw-r--r--test/CodeGen/X86/unaligned-load.ll24
-rw-r--r--test/CodeGen/X86/vec_compare.ll6
-rw-r--r--test/CodeGen/X86/vec_insert-4.ll (renamed from test/CodeGen/X86/vec_insert_4.ll)0
-rw-r--r--test/CodeGen/X86/vec_insert-9.ll9
-rw-r--r--test/CodeGen/X86/vec_return.ll2
-rw-r--r--test/CodeGen/X86/vec_set.ll2
-rw-r--r--test/CodeGen/X86/vec_shuffle-7.ll2
-rw-r--r--test/CodeGen/X86/vec_shuffle-9.ll2
-rw-r--r--test/CodeGen/X86/vec_shuffle.ll3
-rw-r--r--test/CodeGen/X86/vec_zero.ll4
-rw-r--r--test/CodeGen/X86/vec_zero_cse.ll3
-rw-r--r--test/CodeGen/X86/widen_arith-5.ll2
-rw-r--r--test/CodeGen/X86/widen_cast-2.ll2
-rw-r--r--test/CodeGen/X86/widen_load-2.ll46
-rw-r--r--test/CodeGen/X86/xor-icmp.ll4
-rw-r--r--test/CodeGen/X86/xor.ll2
39 files changed, 327 insertions, 129 deletions
diff --git a/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll b/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll
index 5e7c0a7ee2b7..a2288986362e 100644
--- a/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll
+++ b/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll
@@ -1,5 +1,4 @@
; RUN: llc < %s -march=x86-64 > %t
-; RUN: grep leaq %t
; RUN: not grep {,%rsp)} %t
; PR1103
diff --git a/test/CodeGen/X86/2007-04-25-MMX-PADDQ.ll b/test/CodeGen/X86/2007-04-25-MMX-PADDQ.ll
index 113d0eb8647f..c39b82a1fe36 100644
--- a/test/CodeGen/X86/2007-04-25-MMX-PADDQ.ll
+++ b/test/CodeGen/X86/2007-04-25-MMX-PADDQ.ll
@@ -1,12 +1,16 @@
-; RUN: llc < %s -o - -march=x86 -mattr=+mmx | grep paddq | count 2
-; RUN: llc < %s -o - -march=x86 -mattr=+mmx | grep movq | count 2
+; RUN: llc < %s -o - -march=x86 -mattr=+mmx | FileCheck %s
-define <1 x i64> @unsigned_add3(<1 x i64>* %a, <1 x i64>* %b, i32 %count) {
+define <1 x i64> @unsigned_add3(<1 x i64>* %a, <1 x i64>* %b, i32 %count) nounwind {
entry:
%tmp2942 = icmp eq i32 %count, 0 ; <i1> [#uses=1]
br i1 %tmp2942, label %bb31, label %bb26
bb26: ; preds = %bb26, %entry
+
+; CHECK: movq ({{.*}},8), %mm
+; CHECK: paddq ({{.*}},8), %mm
+; CHECK: paddq %mm{{[0-7]}}, %mm
+
%i.037.0 = phi i32 [ 0, %entry ], [ %tmp25, %bb26 ] ; <i32> [#uses=3]
%sum.035.0 = phi <1 x i64> [ zeroinitializer, %entry ], [ %tmp22, %bb26 ] ; <<1 x i64>> [#uses=1]
%tmp13 = getelementptr <1 x i64>* %b, i32 %i.037.0 ; <<1 x i64>*> [#uses=1]
diff --git a/test/CodeGen/X86/2009-02-05-CoalescerBug.ll b/test/CodeGen/X86/2009-02-05-CoalescerBug.ll
index 0ffa8fdc30dd..a46a20b1da65 100644
--- a/test/CodeGen/X86/2009-02-05-CoalescerBug.ll
+++ b/test/CodeGen/X86/2009-02-05-CoalescerBug.ll
@@ -1,5 +1,7 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2,-sse41 | grep movss | count 2
-; RUN: llc < %s -march=x86 -mattr=+sse2,-sse41 | grep movaps | count 4
+; RUN: llc < %s -march=x86 -mattr=+sse2,-sse41 -o %t
+; RUN: grep movss %t | count 2
+; RUN: grep movaps %t | count 2
+; RUN: grep movdqa %t | count 2
define i1 @t([2 x float]* %y, [2 x float]* %w, i32, [2 x float]* %x.pn59, i32 %smax190, i32 %j.1180, <4 x float> %wu.2179, <4 x float> %wr.2178, <4 x float>* %tmp89.out, <4 x float>* %tmp107.out, i32* %indvar.next218.out) nounwind {
newFuncRoot:
diff --git a/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll b/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
index a4d642b40354..d9655fd19b3c 100644
--- a/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
+++ b/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
@@ -1,5 +1,7 @@
-; RUN: llc < %s -march=x86-64 -mattr=+sse3 -stats |& not grep {machine-licm}
+; RUN: llc < %s -march=x86-64 -mattr=+sse3 -stats |& grep {2 machine-licm}
+; RUN: llc < %s -march=x86-64 -mattr=+sse3 | FileCheck %s
; rdar://6627786
+; rdar://7792037
target triple = "x86_64-apple-darwin10.0"
%struct.Key = type { i64 }
@@ -11,6 +13,13 @@ entry:
br label %bb4
bb4: ; preds = %bb.i, %bb26, %bb4, %entry
+; CHECK: %bb4
+; CHECK: xorb
+; CHECK: callq
+; CHECK: movq
+; CHECK: xorl
+; CHECK: xorb
+
%0 = call i32 (...)* @xxGetOffsetForCode(i32 undef) nounwind ; <i32> [#uses=0]
%ins = or i64 %p, 2097152 ; <i64> [#uses=1]
%1 = call i32 (...)* @xxCalculateMidType(%struct.Key* %desc, i32 0) nounwind ; <i32> [#uses=1]
diff --git a/test/CodeGen/X86/2009-11-16-UnfoldMemOpBug.ll b/test/CodeGen/X86/2009-11-16-UnfoldMemOpBug.ll
index 3ce9edb5db44..26bf09c723a0 100644
--- a/test/CodeGen/X86/2009-11-16-UnfoldMemOpBug.ll
+++ b/test/CodeGen/X86/2009-11-16-UnfoldMemOpBug.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 | FileCheck %s
; rdar://7396984
@str = private constant [28 x i8] c"xxxxxxxxxxxxxxxxxxxxxxxxxxx\00", align 1
diff --git a/test/CodeGen/X86/byval7.ll b/test/CodeGen/X86/byval7.ll
index 0da93bad04e1..686ed9c74dde 100644
--- a/test/CodeGen/X86/byval7.ll
+++ b/test/CodeGen/X86/byval7.ll
@@ -1,10 +1,17 @@
-; RUN: llc < %s -march=x86 -mcpu=yonah | egrep {add|lea} | grep 16
+; RUN: llc < %s -march=x86 -mcpu=yonah | FileCheck %s
%struct.S = type { <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>,
+ <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>,
<2 x i64> }
define i32 @main() nounwind {
entry:
+; CHECK: main:
+; CHECK: movl $1, (%esp)
+; CHECK: leal 16(%esp), %edi
+; CHECK: movl $36, %ecx
+; CHECK: leal 160(%esp), %esi
+; CHECK: rep;movsl
%s = alloca %struct.S ; <%struct.S*> [#uses=2]
%tmp15 = getelementptr %struct.S* %s, i32 0, i32 0 ; <<2 x i64>*> [#uses=1]
store <2 x i64> < i64 8589934595, i64 1 >, <2 x i64>* %tmp15, align 16
diff --git a/test/CodeGen/X86/coalesce-esp.ll b/test/CodeGen/X86/coalesce-esp.ll
index 0fe4e56c97ca..e0f2796f9dce 100644
--- a/test/CodeGen/X86/coalesce-esp.ll
+++ b/test/CodeGen/X86/coalesce-esp.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s | grep {movl %esp, %eax}
+; RUN: llc < %s | grep {movl %esp, %ecx}
; PR4572
; Don't coalesce with %esp if it would end up putting %esp in
diff --git a/test/CodeGen/X86/dagcombine-buildvector.ll b/test/CodeGen/X86/dagcombine-buildvector.ll
index c0ee2ac3386b..5cc6eaa405ad 100644
--- a/test/CodeGen/X86/dagcombine-buildvector.ll
+++ b/test/CodeGen/X86/dagcombine-buildvector.ll
@@ -1,11 +1,11 @@
-; RUN: llc < %s -march=x86 -mcpu=penryn -disable-mmx -o %t
-; RUN: grep unpcklpd %t | count 1
-; RUN: grep movapd %t | count 1
-; RUN: grep movaps %t | count 1
+; RUN: llc < %s -march=x86 -mcpu=penryn -disable-mmx | FileCheck %s
; Shows a dag combine bug that will generate an illegal build vector
; with v2i64 build_vector i32, i32.
+; CHECK: test:
+; CHECK: unpcklpd
+; CHECK: movapd
define void @test(<2 x double>* %dst, <4 x double> %src) nounwind {
entry:
%tmp7.i = shufflevector <4 x double> %src, <4 x double> undef, <2 x i32> < i32 0, i32 2 >
@@ -13,6 +13,8 @@ entry:
ret void
}
+; CHECK: test2:
+; CHECK: movdqa
define void @test2(<4 x i16>* %src, <4 x i32>* %dest) nounwind {
entry:
%tmp1 = load <4 x i16>* %src
diff --git a/test/CodeGen/X86/gather-addresses.ll b/test/CodeGen/X86/gather-addresses.ll
index 3e730de0a8e5..134ee28df6c8 100644
--- a/test/CodeGen/X86/gather-addresses.ll
+++ b/test/CodeGen/X86/gather-addresses.ll
@@ -5,7 +5,7 @@
; bounce the vector off of cache rather than shuffling each individual
; element out of the index vector.
-; CHECK: pand (%rdx), %xmm0
+; CHECK: andps (%rdx), %xmm0
; CHECK: movaps %xmm0, -24(%rsp)
; CHECK: movslq -24(%rsp), %rax
; CHECK: movsd (%rdi,%rax,8), %xmm0
diff --git a/test/CodeGen/X86/licm-symbol.ll b/test/CodeGen/X86/licm-symbol.ll
index d61bbfccbc96..08306c2950e2 100644
--- a/test/CodeGen/X86/licm-symbol.ll
+++ b/test/CodeGen/X86/licm-symbol.ll
@@ -3,7 +3,7 @@
; MachineLICM should be able to hoist the sF reference out of the loop.
; CHECK: pushl %esi
-; CHECK: subl $8, %esp
+; CHECK: subl $4, %esp
; CHECK: movl $176, %esi
; CHECK: addl L___sF$non_lazy_ptr, %esi
; CHECK: .align 4, 0x90
diff --git a/test/CodeGen/X86/memcpy-2.ll b/test/CodeGen/X86/memcpy-2.ll
index 2dc939e666ff..4fe32d974d05 100644
--- a/test/CodeGen/X86/memcpy-2.ll
+++ b/test/CodeGen/X86/memcpy-2.ll
@@ -1,15 +1,122 @@
-; RUN: llc < %s -march=x86 -mattr=-sse -mtriple=i686-apple-darwin8.8.0 | grep mov | count 7
-; RUN: llc < %s -march=x86 -mattr=+sse -mtriple=i686-apple-darwin8.8.0 | grep mov | count 5
+; RUN: llc < %s -mattr=+sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE2
+; RUN: llc < %s -mattr=+sse,-sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE1
+; RUN: llc < %s -mattr=-sse -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=NOSSE
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=X86-64
%struct.ParmT = type { [25 x i8], i8, i8* }
@.str12 = internal constant [25 x i8] c"image\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00" ; <[25 x i8]*> [#uses=1]
-declare void @llvm.memcpy.i32(i8*, i8*, i32, i32) nounwind
-
-define void @t(i32 %argc, i8** %argv) nounwind {
+define void @t1(i32 %argc, i8** %argv) nounwind {
entry:
+; SSE2: t1:
+; SSE2: movaps _.str12, %xmm0
+; SSE2: movaps %xmm0
+; SSE2: movb $0
+; SSE2: movl $0
+; SSE2: movl $0
+
+; SSE1: t1:
+; SSE1: movaps _.str12, %xmm0
+; SSE1: movaps %xmm0
+; SSE1: movb $0
+; SSE1: movl $0
+; SSE1: movl $0
+
+; NOSSE: t1:
+; NOSSE: movb $0
+; NOSSE: movl $0
+; NOSSE: movl $0
+; NOSSE: movl $0
+; NOSSE: movl $0
+; NOSSE: movl $101
+; NOSSE: movl $1734438249
+
+; X86-64: t1:
+; X86-64: movaps _.str12(%rip), %xmm0
+; X86-64: movaps %xmm0
+; X86-64: movb $0
+; X86-64: movq $0
%parms.i = alloca [13 x %struct.ParmT] ; <[13 x %struct.ParmT]*> [#uses=1]
%parms1.i = getelementptr [13 x %struct.ParmT]* %parms.i, i32 0, i32 0, i32 0, i32 0 ; <i8*> [#uses=1]
call void @llvm.memcpy.i32( i8* %parms1.i, i8* getelementptr ([25 x i8]* @.str12, i32 0, i32 0), i32 25, i32 1 ) nounwind
unreachable
}
+
+;rdar://7774704
+%struct.s0 = type { [2 x double] }
+
+define void @t2(%struct.s0* nocapture %a, %struct.s0* nocapture %b) nounwind ssp {
+entry:
+; SSE2: t2:
+; SSE2: movaps (%eax), %xmm0
+; SSE2: movaps %xmm0, (%eax)
+
+; SSE1: t2:
+; SSE1: movaps (%eax), %xmm0
+; SSE1: movaps %xmm0, (%eax)
+
+; NOSSE: t2:
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+
+; X86-64: t2:
+; X86-64: movaps (%rsi), %xmm0
+; X86-64: movaps %xmm0, (%rdi)
+ %tmp2 = bitcast %struct.s0* %a to i8* ; <i8*> [#uses=1]
+ %tmp3 = bitcast %struct.s0* %b to i8* ; <i8*> [#uses=1]
+ tail call void @llvm.memcpy.i32(i8* %tmp2, i8* %tmp3, i32 16, i32 16)
+ ret void
+}
+
+define void @t3(%struct.s0* nocapture %a, %struct.s0* nocapture %b) nounwind ssp {
+entry:
+; SSE2: t3:
+; SSE2: movsd (%eax), %xmm0
+; SSE2: movsd 8(%eax), %xmm1
+; SSE2: movsd %xmm1, 8(%eax)
+; SSE2: movsd %xmm0, (%eax)
+
+; SSE1: t3:
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+; SSE1: movl
+
+; NOSSE: t3:
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+; NOSSE: movl
+
+; X86-64: t3:
+; X86-64: movq (%rsi), %rax
+; X86-64: movq 8(%rsi), %rcx
+; X86-64: movq %rcx, 8(%rdi)
+; X86-64: movq %rax, (%rdi)
+ %tmp2 = bitcast %struct.s0* %a to i8* ; <i8*> [#uses=1]
+ %tmp3 = bitcast %struct.s0* %b to i8* ; <i8*> [#uses=1]
+ tail call void @llvm.memcpy.i32(i8* %tmp2, i8* %tmp3, i32 16, i32 8)
+ ret void
+}
+
+declare void @llvm.memcpy.i32(i8* nocapture, i8* nocapture, i32, i32) nounwind
diff --git a/test/CodeGen/X86/memset-2.ll b/test/CodeGen/X86/memset-2.ll
index 7deb52f8078e..702632cde965 100644
--- a/test/CodeGen/X86/memset-2.ll
+++ b/test/CodeGen/X86/memset-2.ll
@@ -1,47 +1,21 @@
-; RUN: llc < %s | not grep rep
-; RUN: llc < %s | grep memset
+; RUN: llc < %s | FileCheck %s
target triple = "i386"
declare void @llvm.memset.i32(i8*, i8, i32, i32) nounwind
-define fastcc i32 @cli_scanzip(i32 %desc) nounwind {
+define fastcc void @t1() nounwind {
entry:
- br label %bb8.i.i.i.i
-
-bb8.i.i.i.i: ; preds = %bb8.i.i.i.i, %entry
- icmp eq i32 0, 0 ; <i1>:0 [#uses=1]
- br i1 %0, label %bb61.i.i.i, label %bb8.i.i.i.i
-
-bb32.i.i.i: ; preds = %bb61.i.i.i
- ptrtoint i8* %tail.0.i.i.i to i32 ; <i32>:1 [#uses=1]
- sub i32 0, %1 ; <i32>:2 [#uses=1]
- icmp sgt i32 %2, 19 ; <i1>:3 [#uses=1]
- br i1 %3, label %bb34.i.i.i, label %bb61.i.i.i
-
-bb34.i.i.i: ; preds = %bb32.i.i.i
- load i32* null, align 4 ; <i32>:4 [#uses=1]
- icmp eq i32 %4, 101010256 ; <i1>:5 [#uses=1]
- br i1 %5, label %bb8.i11.i.i.i, label %bb61.i.i.i
-
-bb8.i11.i.i.i: ; preds = %bb8.i11.i.i.i, %bb34.i.i.i
- icmp eq i32 0, 0 ; <i1>:6 [#uses=1]
- br i1 %6, label %cli_dbgmsg.exit49.i, label %bb8.i11.i.i.i
-
-cli_dbgmsg.exit49.i: ; preds = %bb8.i11.i.i.i
- icmp eq [32768 x i8]* null, null ; <i1>:7 [#uses=1]
- br i1 %7, label %bb1.i28.i, label %bb8.i.i
-
-bb61.i.i.i: ; preds = %bb61.i.i.i, %bb34.i.i.i, %bb32.i.i.i, %bb8.i.i.i.i
- %tail.0.i.i.i = getelementptr [1024 x i8]* null, i32 0, i32 0 ; <i8*> [#uses=2]
- load i8* %tail.0.i.i.i, align 1 ; <i8>:8 [#uses=1]
- icmp eq i8 %8, 80 ; <i1>:9 [#uses=1]
- br i1 %9, label %bb32.i.i.i, label %bb61.i.i.i
-
-bb1.i28.i: ; preds = %cli_dbgmsg.exit49.i
- call void @llvm.memset.i32( i8* null, i8 0, i32 88, i32 1 ) nounwind
- unreachable
+; CHECK: t1:
+; CHECK: call memset
+ call void @llvm.memset.i32( i8* null, i8 0, i32 188, i32 1 ) nounwind
+ unreachable
+}
-bb8.i.i: ; preds = %bb8.i.i, %cli_dbgmsg.exit49.i
- br label %bb8.i.i
+define fastcc void @t2(i8 signext %c) nounwind {
+entry:
+; CHECK: t2:
+; CHECK: call memset
+ call void @llvm.memset.i32( i8* undef, i8 %c, i32 76, i32 1 ) nounwind
+ unreachable
}
diff --git a/test/CodeGen/X86/memset64-on-x86-32.ll b/test/CodeGen/X86/memset64-on-x86-32.ll
index da8fc51da8e1..c0cd271d985e 100644
--- a/test/CodeGen/X86/memset64-on-x86-32.ll
+++ b/test/CodeGen/X86/memset64-on-x86-32.ll
@@ -1,5 +1,6 @@
-; RUN: llc < %s -mtriple=i386-apple-darwin | grep stosl
-; RUN: llc < %s -mtriple=x86_64-apple-darwin | grep movq | count 10
+; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=nehalem | grep movaps | count 5
+; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=core2 | grep movl | count 20
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | grep movq | count 10
define void @bork() nounwind {
entry:
diff --git a/test/CodeGen/X86/pic.ll b/test/CodeGen/X86/pic.ll
index e997233a5194..35b172509c95 100644
--- a/test/CodeGen/X86/pic.ll
+++ b/test/CodeGen/X86/pic.ll
@@ -194,10 +194,10 @@ bb12:
; LINUX: .LJTI8_0:
; LINUX: .long .LBB8_2@GOTOFF
-; LINUX: .long .LBB8_2@GOTOFF
-; LINUX: .long .LBB8_7@GOTOFF
-; LINUX: .long .LBB8_3@GOTOFF
-; LINUX: .long .LBB8_7@GOTOFF
+; LINUX: .long .LBB8_8@GOTOFF
+; LINUX: .long .LBB8_14@GOTOFF
+; LINUX: .long .LBB8_9@GOTOFF
+; LINUX: .long .LBB8_10@GOTOFF
}
declare void @foo1(...)
diff --git a/test/CodeGen/X86/pmul.ll b/test/CodeGen/X86/pmul.ll
index e2746a8c0638..bf5229aa1ee8 100644
--- a/test/CodeGen/X86/pmul.ll
+++ b/test/CodeGen/X86/pmul.ll
@@ -1,6 +1,6 @@
; RUN: llc < %s -march=x86 -mattr=sse41 -stack-alignment=16 > %t
; RUN: grep pmul %t | count 12
-; RUN: grep mov %t | count 12
+; RUN: grep mov %t | count 11
define <4 x i32> @a(<4 x i32> %i) nounwind {
%A = mul <4 x i32> %i, < i32 117, i32 117, i32 117, i32 117 >
diff --git a/test/CodeGen/X86/pmulld.ll b/test/CodeGen/X86/pmulld.ll
new file mode 100644
index 000000000000..3ef594112b45
--- /dev/null
+++ b/test/CodeGen/X86/pmulld.ll
@@ -0,0 +1,16 @@
+; RUN: llc < %s -march=x86-64 -mattr=+sse41 -asm-verbose=0 | FileCheck %s
+
+define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) nounwind {
+; CHECK: test1:
+; CHECK-NEXT: pmulld
+ %C = mul <4 x i32> %A, %B
+ ret <4 x i32> %C
+}
+
+define <4 x i32> @test1a(<4 x i32> %A, <4 x i32> *%Bp) nounwind {
+; CHECK: test1a:
+; CHECK-NEXT: pmulld
+ %B = load <4 x i32>* %Bp
+ %C = mul <4 x i32> %A, %B
+ ret <4 x i32> %C
+}
diff --git a/test/CodeGen/X86/postalloc-coalescing.ll b/test/CodeGen/X86/postalloc-coalescing.ll
index a171436543c6..fe6f521f4d32 100644
--- a/test/CodeGen/X86/postalloc-coalescing.ll
+++ b/test/CodeGen/X86/postalloc-coalescing.ll
@@ -1,6 +1,6 @@
; RUN: llc < %s -march=x86 | grep mov | count 3
-define fastcc i32 @_Z18yy_get_next_bufferv() {
+define fastcc i32 @_Z18yy_get_next_bufferv() nounwind {
entry:
br label %bb131
diff --git a/test/CodeGen/X86/pr2659.ll b/test/CodeGen/X86/pr2659.ll
index 0760e4c7fd5b..27047dfdfd8c 100644
--- a/test/CodeGen/X86/pr2659.ll
+++ b/test/CodeGen/X86/pr2659.ll
@@ -1,4 +1,5 @@
; RUN: llc < %s -march=x86 -mtriple=i686-apple-darwin9.4.0 | grep movl | count 5
+; RUN: llc < %s -march=x86 -mtriple=i686-apple-darwin9.4.0 | FileCheck %s
; PR2659
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
@@ -13,6 +14,11 @@ forcond.preheader: ; preds = %entry
%cmp44 = icmp eq i32 %k, 0 ; <i1> [#uses=1]
br i1 %cmp44, label %afterfor, label %forbody
+; CHECK: %forcond.preheader.forbody_crit_edge
+; CHECK: movl $1
+; CHECK-NOT: xorl
+; CHECK-NEXT: movl $1
+
ifthen: ; preds = %entry
ret i32 0
diff --git a/test/CodeGen/X86/sibcall.ll b/test/CodeGen/X86/sibcall.ll
index ce35b4545184..8e52a7cbfe78 100644
--- a/test/CodeGen/X86/sibcall.ll
+++ b/test/CodeGen/X86/sibcall.ll
@@ -271,3 +271,45 @@ entry:
}
declare double @bar4()
+
+; rdar://6283267
+define void @t17() nounwind ssp {
+entry:
+; 32: t17:
+; 32: jmp {{_?}}bar5
+
+; 64: t17:
+; 64: xorb %al, %al
+; 64: jmp {{_?}}bar5
+ tail call void (...)* @bar5() nounwind
+ ret void
+}
+
+declare void @bar5(...)
+
+; rdar://7774847
+define void @t18() nounwind ssp {
+entry:
+; 32: t18:
+; 32: call {{_?}}bar6
+; 32: fstp %st(0)
+
+; 64: t18:
+; 64: xorb %al, %al
+; 64: jmp {{_?}}bar6
+ %0 = tail call double (...)* @bar6() nounwind
+ ret void
+}
+
+declare double @bar6(...)
+
+define void @t19() alignstack(32) nounwind {
+entry:
+; CHECK: t19:
+; CHECK: andl $-32
+; CHECK: call {{_?}}foo
+ tail call void @foo() nounwind
+ ret void
+}
+
+declare void @foo()
diff --git a/test/CodeGen/X86/small-byval-memcpy.ll b/test/CodeGen/X86/small-byval-memcpy.ll
index 9ec9182e5e3c..1b596b589899 100644
--- a/test/CodeGen/X86/small-byval-memcpy.ll
+++ b/test/CodeGen/X86/small-byval-memcpy.ll
@@ -1,7 +1,5 @@
-; RUN: llc < %s | not grep movs
-
-target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
-target triple = "i386-apple-darwin8"
+; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=core2 | grep movsd | count 8
+; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=nehalem | grep movups | count 2
define void @ccosl({ x86_fp80, x86_fp80 }* noalias sret %agg.result, { x86_fp80, x86_fp80 }* byval align 4 %z) nounwind {
entry:
diff --git a/test/CodeGen/X86/sse-align-12.ll b/test/CodeGen/X86/sse-align-12.ll
index 4f025b916fd9..118e393b7baa 100644
--- a/test/CodeGen/X86/sse-align-12.ll
+++ b/test/CodeGen/X86/sse-align-12.ll
@@ -1,10 +1,8 @@
-; RUN: llc < %s -march=x86-64 > %t
-; RUN: grep unpck %t | count 2
-; RUN: grep shuf %t | count 2
-; RUN: grep ps %t | count 4
-; RUN: grep pd %t | count 4
-; RUN: grep movup %t | count 4
+; RUN: llc < %s -march=x86-64 | FileCheck %s
+; CHECK: a:
+; CHECK: movdqu
+; CHECK: pshufd
define <4 x float> @a(<4 x float>* %y) nounwind {
%x = load <4 x float>* %y, align 4
%a = extractelement <4 x float> %x, i32 0
@@ -17,6 +15,10 @@ define <4 x float> @a(<4 x float>* %y) nounwind {
%s = insertelement <4 x float> %r, float %a, i32 3
ret <4 x float> %s
}
+
+; CHECK: b:
+; CHECK: movups
+; CHECK: unpckhps
define <4 x float> @b(<4 x float>* %y, <4 x float> %z) nounwind {
%x = load <4 x float>* %y, align 4
%a = extractelement <4 x float> %x, i32 2
@@ -29,6 +31,10 @@ define <4 x float> @b(<4 x float>* %y, <4 x float> %z) nounwind {
%s = insertelement <4 x float> %r, float %b, i32 3
ret <4 x float> %s
}
+
+; CHECK: c:
+; CHECK: movupd
+; CHECK: shufpd
define <2 x double> @c(<2 x double>* %y) nounwind {
%x = load <2 x double>* %y, align 8
%a = extractelement <2 x double> %x, i32 0
@@ -37,6 +43,10 @@ define <2 x double> @c(<2 x double>* %y) nounwind {
%r = insertelement <2 x double> %p, double %a, i32 1
ret <2 x double> %r
}
+
+; CHECK: d:
+; CHECK: movupd
+; CHECK: unpckhpd
define <2 x double> @d(<2 x double>* %y, <2 x double> %z) nounwind {
%x = load <2 x double>* %y, align 8
%a = extractelement <2 x double> %x, i32 1
diff --git a/test/CodeGen/X86/sse-align-6.ll b/test/CodeGen/X86/sse-align-6.ll
index 0bbf4228a40b..fcea1b102a20 100644
--- a/test/CodeGen/X86/sse-align-6.ll
+++ b/test/CodeGen/X86/sse-align-6.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86-64 | grep movups | count 1
+; RUN: llc < %s -march=x86-64 | grep movdqu | count 1
define <2 x i64> @bar(<2 x i64>* %p, <2 x i64> %x) nounwind {
%t = load <2 x i64>* %p, align 8
diff --git a/test/CodeGen/X86/sse3.ll b/test/CodeGen/X86/sse3.ll
index e9c2c01a9e44..b969ecb41420 100644
--- a/test/CodeGen/X86/sse3.ll
+++ b/test/CodeGen/X86/sse3.ll
@@ -20,7 +20,7 @@ entry:
; X64: pshuflw $0, %xmm0, %xmm0
; X64: xorl %eax, %eax
; X64: pinsrw $0, %eax, %xmm0
-; X64: movaps %xmm0, (%rdi)
+; X64: movdqa %xmm0, (%rdi)
; X64: ret
}
@@ -32,7 +32,7 @@ define <8 x i16> @t1(<8 x i16>* %A, <8 x i16>* %B) nounwind {
; X64: t1:
; X64: movl (%rsi), %eax
-; X64: movaps (%rdi), %xmm0
+; X64: movdqa (%rdi), %xmm0
; X64: pinsrw $0, %eax, %xmm0
; X64: ret
}
@@ -66,7 +66,7 @@ define <8 x i16> @t4(<8 x i16> %A, <8 x i16> %B) nounwind {
; X64: pshufhw $100, %xmm0, %xmm2
; X64: pinsrw $1, %eax, %xmm2
; X64: pextrw $1, %xmm0, %eax
-; X64: movaps %xmm2, %xmm0
+; X64: movdqa %xmm2, %xmm0
; X64: pinsrw $4, %eax, %xmm0
; X64: ret
}
@@ -122,7 +122,7 @@ define void @t8(<2 x i64>* %res, <2 x i64>* %A) nounwind {
; X64: t8:
; X64: pshuflw $-58, (%rsi), %xmm0
; X64: pshufhw $-58, %xmm0, %xmm0
-; X64: movaps %xmm0, (%rdi)
+; X64: movdqa %xmm0, (%rdi)
; X64: ret
}
diff --git a/test/CodeGen/X86/unaligned-load.ll b/test/CodeGen/X86/unaligned-load.ll
index b61803d10ce4..47b7896bb8f1 100644
--- a/test/CodeGen/X86/unaligned-load.ll
+++ b/test/CodeGen/X86/unaligned-load.ll
@@ -1,4 +1,6 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin10.0 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck %s
+; RUN: llc < %s -mtriple=i386-apple-darwin10.0 -mcpu=core2 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck -check-prefix=I386 %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin10.0 -mcpu=core2 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck -check-prefix=CORE2 %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin10.0 -mcpu=corei7 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck -check-prefix=COREI7 %s
@.str1 = internal constant [31 x i8] c"DHRYSTONE PROGRAM, SOME STRING\00", align 8
@.str3 = internal constant [31 x i8] c"DHRYSTONE PROGRAM, 2'ND STRING\00", align 8
@@ -11,7 +13,15 @@ entry:
bb:
%String2Loc9 = getelementptr inbounds [31 x i8]* %String2Loc, i64 0, i64 0
call void @llvm.memcpy.i64(i8* %String2Loc9, i8* getelementptr inbounds ([31 x i8]* @.str3, i64 0, i64 0), i64 31, i32 1)
-; CHECK: movups _.str3
+; I386: movsd _.str3+16
+; I386: movsd _.str3+8
+; I386: movsd _.str3
+
+; CORE2: movabsq
+; CORE2: movabsq
+; CORE2: movabsq
+
+; COREI7: movups _.str3
br label %bb
return:
@@ -20,8 +30,8 @@ return:
declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
-; CHECK: .align 3
-; CHECK-NEXT: _.str1:
-; CHECK-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING"
-; CHECK: .align 3
-; CHECK-NEXT: _.str3:
+; CORE2: .align 3
+; CORE2-NEXT: _.str1:
+; CORE2-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING"
+; CORE2: .align 3
+; CORE2-NEXT: _.str3:
diff --git a/test/CodeGen/X86/vec_compare.ll b/test/CodeGen/X86/vec_compare.ll
index c8c7257cbb9c..39c9b770d5f4 100644
--- a/test/CodeGen/X86/vec_compare.ll
+++ b/test/CodeGen/X86/vec_compare.ll
@@ -15,7 +15,7 @@ define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK: test2:
; CHECK: pcmp
; CHECK: pcmp
-; CHECK: xorps
+; CHECK: pxor
; CHECK: ret
%C = icmp sge <4 x i32> %A, %B
%D = sext <4 x i1> %C to <4 x i32>
@@ -25,7 +25,7 @@ define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) nounwind {
define <4 x i32> @test3(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK: test3:
; CHECK: pcmpgtd
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: ret
%C = icmp slt <4 x i32> %A, %B
%D = sext <4 x i1> %C to <4 x i32>
@@ -34,7 +34,7 @@ define <4 x i32> @test3(<4 x i32> %A, <4 x i32> %B) nounwind {
define <4 x i32> @test4(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK: test4:
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: pcmpgtd
; CHECK: ret
%C = icmp ugt <4 x i32> %A, %B
diff --git a/test/CodeGen/X86/vec_insert_4.ll b/test/CodeGen/X86/vec_insert-4.ll
index 2c31e56b4af6..2c31e56b4af6 100644
--- a/test/CodeGen/X86/vec_insert_4.ll
+++ b/test/CodeGen/X86/vec_insert-4.ll
diff --git a/test/CodeGen/X86/vec_insert-9.ll b/test/CodeGen/X86/vec_insert-9.ll
new file mode 100644
index 000000000000..2e829df1f8df
--- /dev/null
+++ b/test/CodeGen/X86/vec_insert-9.ll
@@ -0,0 +1,9 @@
+; RUN: llc < %s -march=x86 -mattr=+sse41 > %t
+; RUN: grep pinsrd %t | count 2
+
+define <4 x i32> @var_insert2(<4 x i32> %x, i32 %val, i32 %idx) nounwind {
+entry:
+ %tmp3 = insertelement <4 x i32> undef, i32 %val, i32 0 ; <<4 x i32>> [#uses=1]
+ %tmp4 = insertelement <4 x i32> %tmp3, i32 %idx, i32 3 ; <<4 x i32>> [#uses=1]
+ ret <4 x i32> %tmp4
+}
diff --git a/test/CodeGen/X86/vec_return.ll b/test/CodeGen/X86/vec_return.ll
index 66762b4a0604..676be9b7179c 100644
--- a/test/CodeGen/X86/vec_return.ll
+++ b/test/CodeGen/X86/vec_return.ll
@@ -1,5 +1,5 @@
; RUN: llc < %s -march=x86 -mattr=+sse2 > %t
-; RUN: grep xorps %t | count 1
+; RUN: grep pxor %t | count 1
; RUN: grep movaps %t | count 1
; RUN: not grep shuf %t
diff --git a/test/CodeGen/X86/vec_set.ll b/test/CodeGen/X86/vec_set.ll
index c316df887c16..7f5f8dd213a5 100644
--- a/test/CodeGen/X86/vec_set.ll
+++ b/test/CodeGen/X86/vec_set.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 | grep punpckl | count 7
+; RUN: llc < %s -march=x86 -mattr=+sse2,-sse41 | grep punpckl | count 7
define void @test(<8 x i16>* %b, i16 %a0, i16 %a1, i16 %a2, i16 %a3, i16 %a4, i16 %a5, i16 %a6, i16 %a7) nounwind {
%tmp = insertelement <8 x i16> zeroinitializer, i16 %a0, i32 0 ; <<8 x i16>> [#uses=1]
diff --git a/test/CodeGen/X86/vec_shuffle-7.ll b/test/CodeGen/X86/vec_shuffle-7.ll
index 4cdca09c72f5..64bd6a3c83b8 100644
--- a/test/CodeGen/X86/vec_shuffle-7.ll
+++ b/test/CodeGen/X86/vec_shuffle-7.ll
@@ -1,5 +1,5 @@
; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep xorps %t | count 1
+; RUN: grep pxor %t | count 1
; RUN: not grep shufps %t
define void @test() {
diff --git a/test/CodeGen/X86/vec_shuffle-9.ll b/test/CodeGen/X86/vec_shuffle-9.ll
index fc16a26b6154..07195869b8cf 100644
--- a/test/CodeGen/X86/vec_shuffle-9.ll
+++ b/test/CodeGen/X86/vec_shuffle-9.ll
@@ -1,7 +1,7 @@
; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s
define <4 x i32> @test(i8** %ptr) {
-; CHECK: xorps
+; CHECK: pxor
; CHECK: punpcklbw
; CHECK: punpcklwd
diff --git a/test/CodeGen/X86/vec_shuffle.ll b/test/CodeGen/X86/vec_shuffle.ll
index c05b79a54a15..2a48de22098f 100644
--- a/test/CodeGen/X86/vec_shuffle.ll
+++ b/test/CodeGen/X86/vec_shuffle.ll
@@ -1,5 +1,6 @@
; RUN: llc < %s -march=x86 -mcpu=core2 -o %t
-; RUN: grep shufp %t | count 1
+; RUN: grep movq %t | count 1
+; RUN: grep pshufd %t | count 1
; RUN: grep movupd %t | count 1
; RUN: grep pshufhw %t | count 1
diff --git a/test/CodeGen/X86/vec_zero.ll b/test/CodeGen/X86/vec_zero.ll
index ae5af586cdc3..4d1f05629b41 100644
--- a/test/CodeGen/X86/vec_zero.ll
+++ b/test/CodeGen/X86/vec_zero.ll
@@ -1,5 +1,6 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 | grep xorps | count 2
+; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s
+; CHECK: xorps
define void @foo(<4 x float>* %P) {
%T = load <4 x float>* %P ; <<4 x float>> [#uses=1]
%S = fadd <4 x float> zeroinitializer, %T ; <<4 x float>> [#uses=1]
@@ -7,6 +8,7 @@ define void @foo(<4 x float>* %P) {
ret void
}
+; CHECK: pxor
define void @bar(<4 x i32>* %P) {
%T = load <4 x i32>* %P ; <<4 x i32>> [#uses=1]
%S = add <4 x i32> zeroinitializer, %T ; <<4 x i32>> [#uses=1]
diff --git a/test/CodeGen/X86/vec_zero_cse.ll b/test/CodeGen/X86/vec_zero_cse.ll
index 296378c6e9f5..3b15d4cc407b 100644
--- a/test/CodeGen/X86/vec_zero_cse.ll
+++ b/test/CodeGen/X86/vec_zero_cse.ll
@@ -1,5 +1,4 @@
-; RUN: llc < %s -relocation-model=static -march=x86 -mcpu=yonah | grep pxor | count 1
-; RUN: llc < %s -relocation-model=static -march=x86 -mcpu=yonah | grep xorps | count 1
+; RUN: llc < %s -relocation-model=static -march=x86 -mcpu=yonah | grep pxor | count 2
; RUN: llc < %s -relocation-model=static -march=x86 -mcpu=yonah | grep pcmpeqd | count 2
@M1 = external global <1 x i64>
diff --git a/test/CodeGen/X86/widen_arith-5.ll b/test/CodeGen/X86/widen_arith-5.ll
index f7f340873624..bae5c54eea64 100644
--- a/test/CodeGen/X86/widen_arith-5.ll
+++ b/test/CodeGen/X86/widen_arith-5.ll
@@ -1,5 +1,5 @@
; RUN: llc < %s -march=x86-64 -mattr=+sse42 -disable-mmx | FileCheck %s
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: pmulld
; CHECK: psubd
diff --git a/test/CodeGen/X86/widen_cast-2.ll b/test/CodeGen/X86/widen_cast-2.ll
index 1e626a2f8822..14e8f7562482 100644
--- a/test/CodeGen/X86/widen_cast-2.ll
+++ b/test/CodeGen/X86/widen_cast-2.ll
@@ -2,7 +2,7 @@
; CHECK: pextrd
; CHECK: pextrd
; CHECK: movd
-; CHECK: movaps
+; CHECK: movdqa
; bitcast v14i16 to v7i32
diff --git a/test/CodeGen/X86/widen_load-2.ll b/test/CodeGen/X86/widen_load-2.ll
index 58b557a7915c..658c05143e84 100644
--- a/test/CodeGen/X86/widen_load-2.ll
+++ b/test/CodeGen/X86/widen_load-2.ll
@@ -5,7 +5,7 @@
%i32vec3 = type <3 x i32>
define void @add3i32(%i32vec3* sret %ret, %i32vec3* %ap, %i32vec3* %bp) {
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: paddd
; CHECK: pextrd
; CHECK: movq
@@ -33,13 +33,13 @@ define void @add3i32_2(%i32vec3* sret %ret, %i32vec3* %ap, %i32vec3* %bp) {
%i32vec7 = type <7 x i32>
define void @add7i32(%i32vec7* sret %ret, %i32vec7* %ap, %i32vec7* %bp) {
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
; CHECK: paddd
; CHECK: paddd
; CHECK: pextrd
; CHECK: movq
-; CHECK: movaps
+; CHECK: movdqa
%a = load %i32vec7* %ap, align 16
%b = load %i32vec7* %bp, align 16
%x = add %i32vec7 %a, %b
@@ -49,15 +49,15 @@ define void @add7i32(%i32vec7* sret %ret, %i32vec7* %ap, %i32vec7* %bp) {
%i32vec12 = type <12 x i32>
define void @add12i32(%i32vec12* sret %ret, %i32vec12* %ap, %i32vec12* %bp) {
-; CHECK: movaps
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
+; CHECK: movdqa
; CHECK: paddd
; CHECK: paddd
; CHECK: paddd
-; CHECK: movaps
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
+; CHECK: movdqa
%a = load %i32vec12* %ap, align 16
%b = load %i32vec12* %bp, align 16
%x = add %i32vec12 %a, %b
@@ -68,7 +68,7 @@ define void @add12i32(%i32vec12* sret %ret, %i32vec12* %ap, %i32vec12* %bp) {
%i16vec3 = type <3 x i16>
define void @add3i16(%i16vec3* nocapture sret %ret, %i16vec3* %ap, %i16vec3* %bp) nounwind {
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: paddw
; CHECK: movd
; CHECK: pextrw
@@ -81,7 +81,7 @@ define void @add3i16(%i16vec3* nocapture sret %ret, %i16vec3* %ap, %i16vec3* %bp
%i16vec4 = type <4 x i16>
define void @add4i16(%i16vec4* nocapture sret %ret, %i16vec4* %ap, %i16vec4* %bp) nounwind {
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: paddw
; CHECK: movq
%a = load %i16vec4* %ap, align 16
@@ -93,12 +93,12 @@ define void @add4i16(%i16vec4* nocapture sret %ret, %i16vec4* %ap, %i16vec4* %bp
%i16vec12 = type <12 x i16>
define void @add12i16(%i16vec12* nocapture sret %ret, %i16vec12* %ap, %i16vec12* %bp) nounwind {
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
; CHECK: paddw
; CHECK: paddw
; CHECK: movq
-; CHECK: movaps
+; CHECK: movdqa
%a = load %i16vec12* %ap, align 16
%b = load %i16vec12* %bp, align 16
%x = add %i16vec12 %a, %b
@@ -108,15 +108,15 @@ define void @add12i16(%i16vec12* nocapture sret %ret, %i16vec12* %ap, %i16vec12*
%i16vec18 = type <18 x i16>
define void @add18i16(%i16vec18* nocapture sret %ret, %i16vec18* %ap, %i16vec18* %bp) nounwind {
-; CHECK: movaps
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
+; CHECK: movdqa
; CHECK: paddw
; CHECK: paddw
; CHECK: paddw
; CHECK: movd
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
%a = load %i16vec18* %ap, align 16
%b = load %i16vec18* %bp, align 16
%x = add %i16vec18 %a, %b
@@ -127,7 +127,7 @@ define void @add18i16(%i16vec18* nocapture sret %ret, %i16vec18* %ap, %i16vec18*
%i8vec3 = type <3 x i8>
define void @add3i8(%i8vec3* nocapture sret %ret, %i8vec3* %ap, %i8vec3* %bp) nounwind {
-; CHECK: movaps
+; CHECK: movdqa
; CHECK: paddb
; CHECK: pextrb
; CHECK: movb
@@ -140,8 +140,8 @@ define void @add3i8(%i8vec3* nocapture sret %ret, %i8vec3* %ap, %i8vec3* %bp) no
%i8vec31 = type <31 x i8>
define void @add31i8(%i8vec31* nocapture sret %ret, %i8vec31* %ap, %i8vec31* %bp) nounwind {
-; CHECK: movaps
-; CHECK: movaps
+; CHECK: movdqa
+; CHECK: movdqa
; CHECK: paddb
; CHECK: paddb
; CHECK: movq
diff --git a/test/CodeGen/X86/xor-icmp.ll b/test/CodeGen/X86/xor-icmp.ll
index 2d75c5d76201..34875ed89957 100644
--- a/test/CodeGen/X86/xor-icmp.ll
+++ b/test/CodeGen/X86/xor-icmp.ll
@@ -43,7 +43,7 @@ define i32 @t2(i32 %x, i32 %y) nounwind ssp {
; X32: cmpl
; X32: sete
; X32-NOT: xor
-; X32: je
+; X32: jne
; X64: t2:
; X64: testl
@@ -51,7 +51,7 @@ define i32 @t2(i32 %x, i32 %y) nounwind ssp {
; X64: testl
; X64: sete
; X64-NOT: xor
-; X64: je
+; X64: jne
entry:
%0 = icmp eq i32 %x, 0 ; <i1> [#uses=1]
%1 = icmp eq i32 %y, 0 ; <i1> [#uses=1]
diff --git a/test/CodeGen/X86/xor.ll b/test/CodeGen/X86/xor.ll
index 9bfff8a06a86..f270d9d56e21 100644
--- a/test/CodeGen/X86/xor.ll
+++ b/test/CodeGen/X86/xor.ll
@@ -7,7 +7,7 @@ define <4 x i32> @test1() nounwind {
ret <4 x i32> %tmp
; X32: test1:
-; X32: xorps %xmm0, %xmm0
+; X32: pxor %xmm0, %xmm0
; X32: ret
}