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

[x86] replace integer 'and' ops with packed SSE FP 'and' ops when operating on FP scalars 

Turn this:
   movd %xmm0, %eax
   movd %xmm1, %ecx
   andl %eax, %ecx
   movd %ecx, %xmm0

into this:
   andps %xmm1, %xmm0


This is related to, but does not solve:
https://llvm.org/bugs/show_bug.cgi?id=22428

Differential Revision: http://reviews.llvm.org/D13065

llvm-svn: 248395
This commit is contained in:
Sanjay Patel 2015-09-23 17:00:06 +00:00
parent 979840d31f
commit df2495f331
2 changed files with 22 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -24447,6 +24447,24 @@ static SDValue PerformAndCombine(SDNode *N, SelectionDAG &DAG,
}
} // BEXTR
// If both input operands are being cast from floating point types,
// try to convert this into a floating point logic node to avoid
// unnecessary moves from SSE to integer registers.
// FIXME: Split this into a helper function, so it can also be used with
// or/xor combining.
if (N0.getOpcode() == ISD::BITCAST && N1.getOpcode() == ISD::BITCAST &&
((Subtarget->hasSSE1() && VT == MVT::i32) ||
(Subtarget->hasSSE2() && VT == MVT::i64))) {
SDValue N00 = N0.getOperand(0);
SDValue N10 = N1.getOperand(0);
EVT N00Type = N00.getValueType();
EVT N10Type = N10.getValueType();
if (N00Type.isFloatingPoint() && N10Type.isFloatingPoint()) {
SDValue FLogic = DAG.getNode(X86ISD::FAND, DL, N00Type, N00, N10);
return DAG.getBitcast(VT, FLogic);
}
}
return SDValue();
}

15
llvm/test/CodeGen/X86/fp-logic.ll
View File

@ -142,9 +142,8 @@ define float @f8(float %x) {
define i32 @f9(float %x, float %y) {
; CHECK-LABEL: f9:
; CHECK: # BB#0:
; CHECK-NEXT: movd %xmm0, %ecx
; CHECK-NEXT: movd %xmm1, %eax
; CHECK-NEXT: andl %ecx, %eax
; CHECK-NEXT: andps %xmm1, %xmm0
; CHECK-NEXT: movd %xmm0, %eax
; CHECK-NEXT: retq
%bc1 = bitcast float %x to i32
@ -158,10 +157,7 @@ define i32 @f9(float %x, float %y) {
define float @f10(float %x, float %y) {
; CHECK-LABEL: f10:
; CHECK: # BB#0:
; CHECK-NEXT: movd %xmm0, %eax
; CHECK-NEXT: movd %xmm1, %ecx
; CHECK-NEXT: andl %eax, %ecx
; CHECK-NEXT: movd %ecx, %xmm0
; CHECK-NEXT: andps %xmm1, %xmm0
; CHECK-NEXT: retq
%bc1 = bitcast float %x to i32
@ -208,10 +204,7 @@ define float @xor(float %x, float %y) {
define double @doubles(double %x, double %y) {
; CHECK-LABEL: doubles:
; CHECK: # BB#0:
; CHECK-NEXT: movd %xmm0, %rax
; CHECK-NEXT: movd %xmm1, %rcx
; CHECK-NEXT: andq %rax, %rcx
; CHECK-NEXT: movd %rcx, %xmm0
; CHECK-NEXT: andpd %xmm1, %xmm0
; CHECK-NEXT: retq
%bc1 = bitcast double %x to i64