6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-07-20 10:30:03 +00:00
Code Issues Projects Releases Wiki Activity

Add SSE4A MOVNTSS/MOVNTSD instructions.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156281 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Craig Topper 2012-05-07 05:36:19 +00:00
parent e5076d484b
commit 5f9cccc509
3 changed files with 43 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
include/llvm/IntrinsicsX86.td
View File

@ -1004,6 +1004,16 @@ let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
[IntrNoMem]>;
}
//===----------------------------------------------------------------------===//
// SSE4A
let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
def int_x86_sse4a_movnt_ss : GCCBuiltin<"__builtin_ia32_movntss">,
Intrinsic<[], [llvm_ptr_ty, llvm_v4f32_ty], []>;
def int_x86_sse4a_movnt_sd : GCCBuiltin<"__builtin_ia32_movntsd">,
Intrinsic<[], [llvm_ptr_ty, llvm_v2f64_ty], []>;
}
//===----------------------------------------------------------------------===//
// AVX

14
lib/Target/X86/X86InstrSSE.td
View File

@ -7270,6 +7270,20 @@ defm : pclmul_alias<"hqlq", 0x01>;
defm : pclmul_alias<"lqhq", 0x10>;
defm : pclmul_alias<"lqlq", 0x00>;
//===----------------------------------------------------------------------===//
// SSE4A Instructions
//===----------------------------------------------------------------------===//
let Predicates = [HasSSE4A] in {
def MOVNTSS : I<0x2B, MRMDestMem, (outs), (ins f32mem:$dst, VR128:$src),
"movntss\t{$src, $dst|$dst, $src}",
[(int_x86_sse4a_movnt_ss addr:$dst, VR128:$src)]>, XS;
def MOVNTSD : I<0x2B, MRMDestMem, (outs), (ins f64mem:$dst, VR128:$src),
"movntsd\t{$src, $dst|$dst, $src}",
[(int_x86_sse4a_movnt_sd addr:$dst, VR128:$src)]>, XD;
}
//===----------------------------------------------------------------------===//
// AVX Instructions
//===----------------------------------------------------------------------===//

19
test/CodeGen/X86/sse4a.ll Normal file
View File

@ -0,0 +1,19 @@
; RUN: llc < %s -mtriple=i686-apple-darwin9 -mattr=sse4a | FileCheck %s
define void @test1(float* %p, <4 x float> %a) nounwind optsize ssp {
; CHECK: movntss
entry:
tail call void @llvm.x86.sse4a.movnt.ss(float* %p, <4 x float> %a) nounwind
ret void
}
declare void @llvm.x86.sse4a.movnt.ss(float*, <4 x float>)
define void @test2(double* %p, <2 x double> %a) nounwind optsize ssp {
; CHECK: movntsd
entry:
tail call void @llvm.x86.sse4a.movnt.sd(double* %p, <2 x double> %a) nounwind
ret void
}
declare void @llvm.x86.sse4a.movnt.sd(double*, <2 x double>)