maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/MemCpyOpt/sret.ll

29 lines
1.7 KiB
LLVM
Raw Normal View History

Use opt -S instead of piping bitcode output through llvm-dis. llvm-svn: 81257
2009-09-09 06:34:10 +08:00
; RUN: opt %s -memcpyopt -S | not grep {call.*memcpy}
Add support to GVN for performing sret return slot optimization. This means that, if an sret function tail calls another sret function, it should pass its own sret parameter to the tail callee, allowing it to fill in the correct return value. llvm-gcc does not emit this by default. Instead, it allocates space in the caller for the sret of the tail call and then uses memcpy to copy the result into the caller's sret parameter. This optimization detects and optimizes that case. llvm-svn: 47265
2008-02-18 17:24:53 +08:00
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 = "i686-apple-darwin9"
define void @ccosl({ x86_fp80, x86_fp80 }* noalias sret %agg.result, { x86_fp80, x86_fp80 }* byval %z) nounwind {
entry:
%iz = alloca { x86_fp80, x86_fp80 } ; <{ x86_fp80, x86_fp80 }*> [#uses=3]
%memtmp = alloca { x86_fp80, x86_fp80 }, align 16 ; <{ x86_fp80, x86_fp80 }*> [#uses=2]
%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]
Split the Add, Sub, and Mul instruction opcodes into separate integer and floating-point opcodes, introducing FAdd, FSub, and FMul. For now, the AsmParser, BitcodeReader, and IRBuilder all preserve backwards compatability, and the Core LLVM APIs preserve backwards compatibility for IR producers. Most front-ends won't need to change immediately. This implements the first step of the plan outlined here: http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt llvm-svn: 72897
2009-06-05 06:49:04 +08:00
%tmp3 = fsub x86_fp80 0xK80000000000000000000, %tmp2 ; <x86_fp80> [#uses=1]
Add support to GVN for performing sret return slot optimization. This means that, if an sret function tail calls another sret function, it should pass its own sret parameter to the tail callee, allowing it to fill in the correct return value. llvm-gcc does not emit this by default. Instead, it allocates space in the caller for the sret of the tail call and then uses memcpy to copy the result into the caller's sret parameter. This optimization detects and optimizes that case. llvm-svn: 47265
2008-02-18 17:24:53 +08:00
%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]
%tmp7 = getelementptr { x86_fp80, x86_fp80 }* %z, i32 0, i32 0 ; <x86_fp80*> [#uses=1]
%tmp8 = load x86_fp80* %tmp7, align 16 ; <x86_fp80> [#uses=1]
store x86_fp80 %tmp3, x86_fp80* %real, align 16
store x86_fp80 %tmp8, x86_fp80* %tmp4, align 16
call void @ccoshl( { x86_fp80, x86_fp80 }* noalias sret %memtmp, { x86_fp80, x86_fp80 }* byval %iz ) nounwind
%memtmp14 = bitcast { x86_fp80, x86_fp80 }* %memtmp to i8* ; <i8*> [#uses=1]
%agg.result15 = bitcast { x86_fp80, x86_fp80 }* %agg.result to i8* ; <i8*> [#uses=1]
call void @llvm.memcpy.i32( i8* %agg.result15, i8* %memtmp14, i32 32, i32 16 )
ret void
}
declare void @ccoshl({ x86_fp80, x86_fp80 }* noalias sret , { x86_fp80, x86_fp80 }* byval ) nounwind
declare void @llvm.memcpy.i32(i8*, i8*, i32, i32) nounwind