Enable all Hexagon tests.

[oota-llvm.git] / test / CodeGen / X86 / memcpy-2.ll

diff --git a/test/CodeGen/X86/memcpy-2.ll b/test/CodeGen/X86/memcpy-2.ll
index 9078e4ba533f92e8b223b52b06b6aabcc00385f8..eae2e708349cd89ea7802616d4da13157965209d 100644 (file)
--- a/test/CodeGen/X86/memcpy-2.ll
+++ b/test/CodeGen/X86/memcpy-2.ll
@@ -1,4 +1,5 @@
 ; 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
 
@@ -14,6 +15,13 @@ entry:
 ; SSE2: movl $0
 ; SSE2: movl $0
 
+; SSE1: t1:
+; SSE1: movaps _.str, %xmm0
+; SSE1: movaps %xmm0
+; SSE1: movb $0
+; SSE1: movl $0
+; SSE1: movl $0
+
 ; NOSSE: t1:
 ; NOSSE: movb $0
 ; NOSSE: movl $0
@@ -30,7 +38,7 @@ entry:
 ; X86-64: movq $0
   %tmp1 = alloca [25 x i8]
   %tmp2 = bitcast [25 x i8]* %tmp1 to i8*
-  call void @llvm.memcpy.i32( i8* %tmp2, i8* getelementptr ([25 x i8]* @.str, i32 0, i32 0), i32 25, i32 1 ) nounwind 
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([25 x i8]* @.str, i32 0, i32 0), i32 25, i32 1, i1 false)
   unreachable
 }
 
@@ -43,6 +51,10 @@ entry:
 ; SSE2: movaps (%eax), %xmm0
 ; SSE2: movaps %xmm0, (%eax)
 
+; SSE1: t2:
+; SSE1: movaps (%eax), %xmm0
+; SSE1: movaps %xmm0, (%eax)
+
 ; NOSSE: t2:
 ; NOSSE: movl
 ; NOSSE: movl
@@ -60,15 +72,29 @@ entry:
 ; 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)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* %tmp3, i32 16, i32 16, i1 false)
   ret void
 }
 
 define void @t3(%struct.s0* nocapture %a, %struct.s0* nocapture %b) nounwind ssp {
 entry:
 ; SSE2: t3:
-; SSE2: movups (%eax), %xmm0
-; SSE2: movups %xmm0, (%eax)
+; 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
@@ -83,23 +109,37 @@ entry:
 ; NOSSE: movl
 
 ; X86-64: t3:
-; X86-64: movups (%rsi), %xmm0
-; X86-64: movups %xmm0, (%rdi)
+; 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)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* %tmp3, i32 16, i32 8, i1 false)
   ret void
 }
 
 define void @t4() nounwind {
 entry:
 ; SSE2: t4:
-; SSE2: movups _.str2, %xmm0
-; SSE2: movaps %xmm0, (%esp)
-; SSE2: movw $120, 28(%esp)
+; SSE2: movw $120
+; SSE2: movl $2021161080
+; SSE2: movl $2021161080
 ; SSE2: movl $2021161080
 ; SSE2: movl $2021161080
 ; SSE2: movl $2021161080
+; SSE2: movl $2021161080
+; SSE2: movl $2021161080
+
+; SSE1: t4:
+; SSE1: movw $120
+; SSE1: movl $2021161080
+; SSE1: movl $2021161080
+; SSE1: movl $2021161080
+; SSE1: movl $2021161080
+; SSE1: movl $2021161080
+; SSE1: movl $2021161080
+; SSE1: movl $2021161080
 
 ; NOSSE: t4:
 ; NOSSE: movw $120
@@ -114,14 +154,14 @@ entry:
 ; X86-64: t4:
 ; X86-64: movabsq $8680820740569200760, %rax
 ; X86-64: movq %rax
-; X86-64: movups _.str2(%rip), %xmm0
-; X86-64: movaps %xmm0, -40(%rsp)
+; X86-64: movq %rax
+; X86-64: movq %rax
 ; X86-64: movw $120
 ; X86-64: movl $2021161080
   %tmp1 = alloca [30 x i8]
   %tmp2 = bitcast [30 x i8]* %tmp1 to i8*
-  call void @llvm.memcpy.i32(i8* %tmp2, i8* getelementptr inbounds ([30 x i8]* @.str2, i32 0, i32 0), i32 30, i32 1)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp2, i8* getelementptr inbounds ([30 x i8]* @.str2, i32 0, i32 0), i32 30, i32 1, i1 false)
   unreachable
 }
 
-declare void @llvm.memcpy.i32(i8* nocapture, i8* nocapture, i32, i32) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind