maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Implement "punpckldq %xmm0, $xmm0" as "pshufd $0x50, %xmm0, %xmm" unless optimizing for code size. 

llvm-svn: 56711
This commit is contained in:
Evan Cheng 2008-09-26 23:41:32 +00:00
parent 8bafa2cf9f
commit 7d6fa97567
5 changed files with 60 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
View File

@ -32,6 +32,7 @@
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/SelectionDAGISel.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/MathExtras.h"
@ -130,12 +131,17 @@ namespace {
///
MachineBasicBlock *CurBB;
/// OptForSize - If true, selector should try to optimize for code size
/// instead of performance.
bool OptForSize;
public:
X86DAGToDAGISel(X86TargetMachine &tm, bool fast)
: SelectionDAGISel(X86Lowering, fast),
ContainsFPCode(false), TM(tm),
X86Lowering(*TM.getTargetLowering()),
Subtarget(&TM.getSubtarget<X86Subtarget>()) {}
Subtarget(&TM.getSubtarget<X86Subtarget>()),
OptForSize(OptimizeForSize) {}
virtual bool runOnFunction(Function &Fn) {
// Make sure we re-emit a set of the global base reg if necessary
@ -650,6 +656,10 @@ void X86DAGToDAGISel::PreprocessForFPConvert() {
/// when it has created a SelectionDAG for us to codegen.
void X86DAGToDAGISel::InstructionSelect() {
CurBB = BB; // BB can change as result of isel.
if (!OptForSize) {
const Function *F = CurDAG->getMachineFunction().getFunction();
OptForSize = !F->isDeclaration() && F->hasNote(Attribute::OptimizeForSize);
}
DEBUG(BB->dump());
if (!Fast)

1
llvm/lib/Target/X86/X86InstrInfo.td
View File

@ -186,6 +186,7 @@ def In64BitMode : Predicate<"Subtarget->is64Bit()">;
def SmallCode : Predicate<"TM.getCodeModel() == CodeModel::Small">;
def NotSmallCode : Predicate<"TM.getCodeModel() != CodeModel::Small">;
def IsStatic : Predicate<"TM.getRelocationModel() == Reloc::Static">;
def OptForSpeed : Predicate<"!OptForSize">;
//===----------------------------------------------------------------------===//
// X86 Instruction Format Definitions.

29
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -744,7 +744,7 @@ def MOVHPSmr : PSI<0x17, MRMDestMem, (outs), (ins f64mem:$dst, VR128:$src),
addr:$dst)]>;
let Constraints = "$src1 = $dst" in {
let AddedComplexity = 15 in {
let AddedComplexity = 20 in {
def MOVLHPSrr : PSI<0x16, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src1, VR128:$src2),
"movlhps\t{$src2, $dst|$dst, $src2}",
[(set VR128:$dst,
@ -759,7 +759,7 @@ def MOVHLPSrr : PSI<0x12, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src1, VR128:
} // AddedComplexity
} // Constraints = "$src1 = $dst"
let AddedComplexity = 15 in
let AddedComplexity = 20 in
def : Pat<(v4f32 (vector_shuffle VR128:$src, (undef), MOVDDUP_shuffle_mask)),
(MOVLHPSrr VR128:$src, VR128:$src)>, Requires<[HasSSE1]>;
@ -2921,6 +2921,7 @@ def : Pat<(vector_shuffle (bc_v4i32 (memopv4f32 addr:$src1)), (undef),
SHUFP_unary_shuffle_mask:$sm),
(PSHUFDmi addr:$src1, SHUFP_unary_shuffle_mask:$sm)>,
Requires<[HasSSE2]>;
// Special binary v4i32 shuffle cases with SHUFPS.
def : Pat<(v4i32 (vector_shuffle VR128:$src1, (v4i32 VR128:$src2),
PSHUFD_binary_shuffle_mask:$sm)),
@ -2937,11 +2938,21 @@ def : Pat<(v2i64 (vector_shuffle VR128:$src1, VR128:$src2,
Requires<[HasSSE2]>;
// Special unary SHUFPDrri case.
def : Pat<(v2i64 (vector_shuffle VR128:$src1, (undef),
SHUFP_unary_shuffle_mask:$sm)),
SHUFP_unary_shuffle_mask:$sm)),
(SHUFPDrri VR128:$src1, VR128:$src1, SHUFP_unary_shuffle_mask:$sm)>,
Requires<[HasSSE2]>;
// vector_shuffle v1, <undef>, <0, 0, 1, 1, ...>
let AddedComplexity = 15 in {
def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
UNPCKL_v_undef_shuffle_mask:$sm)),
(PSHUFDri VR128:$src, PSHUFD_shuffle_mask:$sm)>,
Requires<[OptForSpeed, HasSSE2]>;
def : Pat<(v4f32 (vector_shuffle VR128:$src, (undef),
UNPCKL_v_undef_shuffle_mask:$sm)),
(PSHUFDri VR128:$src, PSHUFD_shuffle_mask:$sm)>,
Requires<[OptForSpeed, HasSSE2]>;
}
let AddedComplexity = 10 in {
def : Pat<(v4f32 (vector_shuffle VR128:$src, (undef),
UNPCKL_v_undef_shuffle_mask)),
@ -2958,6 +2969,16 @@ def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
}
// vector_shuffle v1, <undef>, <2, 2, 3, 3, ...>
let AddedComplexity = 15 in {
def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
UNPCKH_v_undef_shuffle_mask:$sm)),
(PSHUFDri VR128:$src, PSHUFD_shuffle_mask:$sm)>,
Requires<[OptForSpeed, HasSSE2]>;
def : Pat<(v4f32 (vector_shuffle VR128:$src, (undef),
UNPCKH_v_undef_shuffle_mask:$sm)),
(PSHUFDri VR128:$src, PSHUFD_shuffle_mask:$sm)>,
Requires<[OptForSpeed, HasSSE2]>;
}
let AddedComplexity = 10 in {
def : Pat<(v4f32 (vector_shuffle VR128:$src, (undef),
UNPCKH_v_undef_shuffle_mask)),
@ -2973,7 +2994,7 @@ def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
(PUNPCKHDQrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
}
let AddedComplexity = 15 in {
let AddedComplexity = 20 in {
// vector_shuffle v1, v2 <0, 1, 4, 5> using MOVLHPS
def : Pat<(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
MOVHP_shuffle_mask)),

8
llvm/test/CodeGen/X86/vec_extract.ll
View File

@ -4,7 +4,7 @@
; RUN: grep pshufd %t | count 1
; RUN: grep unpckhpd %t | count 1
define void @test1(<4 x float>* %F, float* %f) {
define void @test1(<4 x float>* %F, float* %f) nounwind {
%tmp = load <4 x float>* %F ; <<4 x float>> [#uses=2]
%tmp7 = add <4 x float> %tmp, %tmp ; <<4 x float>> [#uses=1]
%tmp2 = extractelement <4 x float> %tmp7, i32 0 ; <float> [#uses=1]
@ -12,21 +12,21 @@ define void @test1(<4 x float>* %F, float* %f) {
ret void
}
define float @test2(<4 x float>* %F, float* %f) {
define float @test2(<4 x float>* %F, float* %f) nounwind {
%tmp = load <4 x float>* %F ; <<4 x float>> [#uses=2]
%tmp7 = add <4 x float> %tmp, %tmp ; <<4 x float>> [#uses=1]
%tmp2 = extractelement <4 x float> %tmp7, i32 2 ; <float> [#uses=1]
ret float %tmp2
}
define void @test3(float* %R, <4 x float>* %P1) {
define void @test3(float* %R, <4 x float>* %P1) nounwind {
%X = load <4 x float>* %P1 ; <<4 x float>> [#uses=1]
%tmp = extractelement <4 x float> %X, i32 3 ; <float> [#uses=1]
store float %tmp, float* %R
ret void
}
define double @test4(double %A) {
define double @test4(double %A) nounwind {
%tmp1 = call <2 x double> @foo( ) ; <<2 x double>> [#uses=1]
%tmp2 = extractelement <2 x double> %tmp1, i32 1 ; <double> [#uses=1]
%tmp3 = add double %tmp2, %A ; <double> [#uses=1]

19
llvm/test/CodeGen/X86/vec_shuffle-23.ll Normal file
View File

@ -0,0 +1,19 @@
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | not grep punpck
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep pshufd
; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 -optimize-size | grep punpck
define i32 @t() nounwind {
entry:
%a = alloca <4 x i32> ; <<4 x i32>*> [#uses=2]
%b = alloca <4 x i32> ; <<4 x i32>*> [#uses=5]
volatile store <4 x i32> < i32 0, i32 1, i32 2, i32 3 >, <4 x i32>* %a
%tmp = load <4 x i32>* %a ; <<4 x i32>> [#uses=1]
store <4 x i32> %tmp, <4 x i32>* %b
%tmp1 = load <4 x i32>* %b ; <<4 x i32>> [#uses=1]
%tmp2 = load <4 x i32>* %b ; <<4 x i32>> [#uses=1]
%punpckldq = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> < i32 0, i32 4, i32 1, i32 5 > ; <<4 x i32>> [#uses=1]
store <4 x i32> %punpckldq, <4 x i32>* %b
%tmp3 = load <4 x i32>* %b ; <<4 x i32>> [#uses=1]
%result = extractelement <4 x i32> %tmp3, i32 0 ; <i32> [#uses=1]
ret i32 %result
}