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/X86/2004-02-12-Memcpy.ll

26 lines
823 B
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 -march=x86 -mtriple=i686-pc-linux-gnu | grep movs | count 3
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
call libc memcpy/memset if array size is bigger then threshold. Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s) llvm-svn: 41479
2007-08-27 18:18:20 +08:00
@A = global [32 x i32] zeroinitializer
@B = global [32 x i32] zeroinitializer
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
call libc memcpy/memset if array size is bigger then threshold. Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s) llvm-svn: 41479
2007-08-27 18:18:20 +08:00
declare void @llvm.memcpy.i32(i8*, i8*, i32, i32)
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
call libc memcpy/memset if array size is bigger then threshold. Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s) llvm-svn: 41479
2007-08-27 18:18:20 +08:00
define void @main() {
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
; dword copy
call libc memcpy/memset if array size is bigger then threshold. Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s) llvm-svn: 41479
2007-08-27 18:18:20 +08:00
call void @llvm.memcpy.i32(i8* bitcast ([32 x i32]* @A to i8*),
i8* bitcast ([32 x i32]* @B to i8*),
i32 128, i32 4 )
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
; word copy
call libc memcpy/memset if array size is bigger then threshold. Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s) llvm-svn: 41479
2007-08-27 18:18:20 +08:00
call void @llvm.memcpy.i32( i8* bitcast ([32 x i32]* @A to i8*),
i8* bitcast ([32 x i32]* @B to i8*),
i32 128, i32 2 )
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
; byte copy
call libc memcpy/memset if array size is bigger then threshold. Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s) llvm-svn: 41479
2007-08-27 18:18:20 +08:00
call void @llvm.memcpy.i32( i8* bitcast ([32 x i32]* @A to i8*),
i8* bitcast ([32 x i32]* @B to i8*),
i32 128, i32 1 )
Test that we get rep movs when calling memcpy llvm-svn: 11352
2004-02-13 01:53:43 +08:00
ret void
}