maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/small-byval-memcpy.ll

23 lines
1.3 KiB
LLVM
Raw Normal View History

Drop ISD::MEMSET, ISD::MEMMOVE, and ISD::MEMCPY, which are not Legal on any current target and aren't optimized in DAGCombiner. Instead of using intermediate nodes, expand the operations, choosing between simple loads/stores, target-specific code, and library calls, immediately. Previously, the code to emit optimized code for these operations was only used at initial SelectionDAG construction time; now it is used at all times. This fixes some cases where rep;movs was being used for small copies where simple loads/stores would be better. This also cleans up code that checks for alignments less than 4; let the targets make that decision instead of doing it in target-independent code. This allows x86 to use rep;movs in low-alignment cases. Also, this fixes a bug that resulted in the use of rep;stos for memsets of 0 with non-constant memory size when the alignment was at least 4. It's better to use the library in this case, which can be significantly faster when the size is large. This also preserves more SourceValue information when memory intrinsics are lowered into simple loads/stores. llvm-svn: 49572
2008-04-12 12:36:06 +08:00
; RUN: llvm-as < %s | llc | 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"
define void @ccosl({ x86_fp80, x86_fp80 }* noalias sret %agg.result, { x86_fp80, x86_fp80 }* byval align 4 %z) nounwind {
entry:
%iz = alloca { x86_fp80, x86_fp80 } ; <{ x86_fp80, x86_fp80 }*> [#uses=3]
%tmp1 = getelementptr { x86_fp80, x86_fp80 }* %z, i32 0, i32 1 ; <x86_fp80*> [#uses=1]
%tmp2 = load x86_fp80* %tmp1, align 16 ; <x86_fp80> [#uses=1]
%tmp3 = sub x86_fp80 0xK80000000000000000000, %tmp2 ; <x86_fp80> [#uses=1]
%tmp4 = getelementptr { x86_fp80, x86_fp80 }* %iz, i32 0, i32 1 ; <x86_fp80*> [#uses=1]
%real = getelementptr { x86_fp80, x86_fp80 }* %iz, i32 0, i32 0 ; <x86_fp80*> [#uses=1]
%tmp6 = getelementptr { x86_fp80, x86_fp80 }* %z, i32 0, i32 0 ; <x86_fp80*> [#uses=1]
%tmp7 = load x86_fp80* %tmp6, align 16 ; <x86_fp80> [#uses=1]
store x86_fp80 %tmp3, x86_fp80* %real, align 16
store x86_fp80 %tmp7, x86_fp80* %tmp4, align 16
call void @ccoshl( { x86_fp80, x86_fp80 }* noalias sret %agg.result, { x86_fp80, x86_fp80 }* byval align 4 %iz ) nounwind
ret void
}
declare void @ccoshl({ x86_fp80, x86_fp80 }* noalias sret , { x86_fp80, x86_fp80 }* byval align 4 ) nounwind