In 64-bit mode, use i64 to lower memcpy / memset instead of f64.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@100137 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 11d6ec11ba37a2f8439afac6af2c93297cc87f03..834ef6c4233d6856456ca03e35cf4020a9c2f2cb 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -1097,6 +1097,7 @@ X86TargetLowering::getOptimalMemOpType(uint64_t Size,
         return MVT::v4f32;
     } else if (SafeToUseFP &&
                Size >= 8 &&
+               !Subtarget->is64Bit() &&
                Subtarget->getStackAlignment() >= 8 &&
                Subtarget->hasSSE2())
       return MVT::f64;

diff --git a/test/CodeGen/X86/memcpy-2.ll b/test/CodeGen/X86/memcpy-2.ll
index 68594f663fb390035bd508a343ff70633703c3e0..4fe32d974d05caeecb6f104b5c83a1ffcb424b10 100644 (file)
--- a/test/CodeGen/X86/memcpy-2.ll
+++ b/test/CodeGen/X86/memcpy-2.ll
@@ -1,6 +1,7 @@
 ; 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]
@@ -29,6 +30,12 @@ entry:
 ; 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 
@@ -59,6 +66,10 @@ entry:
 ; 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)
@@ -96,6 +107,12 @@ entry:
 ; 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)

diff --git a/test/CodeGen/X86/unaligned-load.ll b/test/CodeGen/X86/unaligned-load.ll
index 2e9b248314c10852349f80216a2b27a4aacd622c..47b7896bb8f1d86c211ce2dacfa9d1c486f49273 100644 (file)
--- a/test/CodeGen/X86/unaligned-load.ll
+++ b/test/CodeGen/X86/unaligned-load.ll
@@ -1,3 +1,4 @@
+; 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
 
@@ -12,9 +13,13 @@ 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)
-; CORE2: movsd _.str3+16
-; CORE2: movsd _.str3+8
-; CORE2: movsd _.str3
+; I386: movsd _.str3+16
+; I386: movsd _.str3+8
+; I386: movsd _.str3
+
+; CORE2: movabsq
+; CORE2: movabsq
+; CORE2: movabsq
 
 ; COREI7: movups _.str3
   br label %bb
@@ -30,9 +35,3 @@ declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
 ; CORE2-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING"
 ; CORE2: .align 3
 ; CORE2-NEXT: _.str3:
-
-; COREI7: .align  3
-; COREI7-NEXT: _.str1:
-; COREI7-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING"
-; COREI7: .align 3
-; COREI7-NEXT: _.str3: