[llvm] r368490 - [DAGCombiner] exclude x*2.0 from normal negation profitability rules
Sanjay Patel via llvm-commits
llvm-commits at lists.llvm.org
Fri Aug 9 14:37:32 PDT 2019
Author: spatel
Date: Fri Aug 9 14:37:32 2019
New Revision: 368490
URL: http://llvm.org/viewvc/llvm-project?rev=368490&view=rev
Log:
[DAGCombiner] exclude x*2.0 from normal negation profitability rules
This is the codegen part of fixing:
https://bugs.llvm.org/show_bug.cgi?id=32939
Even with the optimal/canonical IR that is ideally created by D65954,
we would reverse that transform in DAGCombiner and end up with the same
asm on AArch64 or x86.
I see 2 options for trying to correct this:
1. Limit isNegatibleForFree() by special-casing the fmul pattern (this patch).
2. Avoid creating (fmul X, 2.0) in the 1st place by adding a special-case
transform to SelectionDAG::getNode() and/or SelectionDAGBuilder::visitFMul()
that matches the transform done by DAGCombiner.
This seems like the less intrusive patch, but if there's some other reason to
prefer 1 option over the other, we can change to the other option.
Differential Revision: https://reviews.llvm.org/D66016
Modified:
llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
llvm/trunk/test/CodeGen/AArch64/fadd-combines.ll
llvm/trunk/test/CodeGen/X86/fadd-combines.ll
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp?rev=368490&r1=368489&r2=368490&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp Fri Aug 9 14:37:32 2019
@@ -868,6 +868,11 @@ static char isNegatibleForFree(SDValue O
Options, ForCodeSize, Depth + 1))
return V;
+ // Ignore X * 2.0 because that is expected to be canonicalized to X + X.
+ if (auto *C = isConstOrConstSplatFP(Op.getOperand(1)))
+ if (C->isExactlyValue(2.0) && Op.getOpcode() == ISD::FMUL)
+ return 0;
+
return isNegatibleForFree(Op.getOperand(1), LegalOperations, TLI, Options,
ForCodeSize, Depth + 1);
Modified: llvm/trunk/test/CodeGen/AArch64/fadd-combines.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AArch64/fadd-combines.ll?rev=368490&r1=368489&r2=368490&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AArch64/fadd-combines.ll (original)
+++ llvm/trunk/test/CodeGen/AArch64/fadd-combines.ll Fri Aug 9 14:37:32 2019
@@ -169,10 +169,9 @@ define float @fadd_const_multiuse_attr(f
define double @fmul2_negated(double %a, double %b, double %c) {
; CHECK-LABEL: fmul2_negated:
; CHECK: // %bb.0:
-; CHECK-NEXT: fmov d3, #-2.00000000
-; CHECK-NEXT: fmul d1, d1, d3
+; CHECK-NEXT: fadd d1, d1, d1
; CHECK-NEXT: fmul d1, d1, d2
-; CHECK-NEXT: fadd d0, d0, d1
+; CHECK-NEXT: fsub d0, d0, d1
; CHECK-NEXT: ret
%mul = fmul double %b, 2.0
%mul1 = fmul double %mul, %c
@@ -183,10 +182,9 @@ define double @fmul2_negated(double %a,
define <2 x double> @fmul2_negated_vec(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-LABEL: fmul2_negated_vec:
; CHECK: // %bb.0:
-; CHECK-NEXT: fmov v3.2d, #-2.00000000
-; CHECK-NEXT: fmul v1.2d, v1.2d, v3.2d
+; CHECK-NEXT: fadd v1.2d, v1.2d, v1.2d
; CHECK-NEXT: fmul v1.2d, v1.2d, v2.2d
-; CHECK-NEXT: fadd v0.2d, v0.2d, v1.2d
+; CHECK-NEXT: fsub v0.2d, v0.2d, v1.2d
; CHECK-NEXT: ret
%mul = fmul <2 x double> %b, <double 2.0, double 2.0>
%mul1 = fmul <2 x double> %mul, %c
Modified: llvm/trunk/test/CodeGen/X86/fadd-combines.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/fadd-combines.ll?rev=368490&r1=368489&r2=368490&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/fadd-combines.ll (original)
+++ llvm/trunk/test/CodeGen/X86/fadd-combines.ll Fri Aug 9 14:37:32 2019
@@ -252,9 +252,9 @@ define float @fadd_const_multiuse_attr(f
define double @fmul2_negated(double %a, double %b, double %c) {
; CHECK-LABEL: fmul2_negated:
; CHECK: # %bb.0:
-; CHECK-NEXT: mulsd {{.*}}(%rip), %xmm1
+; CHECK-NEXT: addsd %xmm1, %xmm1
; CHECK-NEXT: mulsd %xmm2, %xmm1
-; CHECK-NEXT: addsd %xmm1, %xmm0
+; CHECK-NEXT: subsd %xmm1, %xmm0
; CHECK-NEXT: retq
%mul = fmul double %b, 2.0
%mul1 = fmul double %mul, %c
@@ -265,9 +265,9 @@ define double @fmul2_negated(double %a,
define <2 x double> @fmul2_negated_vec(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-LABEL: fmul2_negated_vec:
; CHECK: # %bb.0:
-; CHECK-NEXT: mulpd {{.*}}(%rip), %xmm1
+; CHECK-NEXT: addpd %xmm1, %xmm1
; CHECK-NEXT: mulpd %xmm2, %xmm1
-; CHECK-NEXT: addpd %xmm1, %xmm0
+; CHECK-NEXT: subpd %xmm1, %xmm0
; CHECK-NEXT: retq
%mul = fmul <2 x double> %b, <double 2.0, double 2.0>
%mul1 = fmul <2 x double> %mul, %c
More information about the llvm-commits
mailing list