[PATCH] D72015: DAG: Stop trying to fold FP -(x-y) -> y-x in getNode with nsz
Matt Arsenault via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Tue Dec 31 12:05:54 PST 2019
arsenm updated this revision to Diff 235726.
arsenm added a comment.
Rebase. New AArch64 test looks like an improvement
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D72015/new/
https://reviews.llvm.org/D72015
Files:
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
llvm/test/CodeGen/AArch64/arm64-fp.ll
llvm/test/CodeGen/AMDGPU/fneg-fold-legalize-dag-increase-insts.ll
Index: llvm/test/CodeGen/AMDGPU/fneg-fold-legalize-dag-increase-insts.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/fneg-fold-legalize-dag-increase-insts.ll
+++ llvm/test/CodeGen/AMDGPU/fneg-fold-legalize-dag-increase-insts.ll
@@ -1,8 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-no-signed-zeros-fp-math=true < %s | FileCheck %s
-
-; FIXME: This should be the same when the extra instructions are fixed
-; XUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-no-signed-zeros-fp-math=false < %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-no-signed-zeros-fp-math=false < %s | FileCheck %s
; no-signed-zeros-fp-math should not increase the number of
; instructions emitted.
@@ -11,10 +9,9 @@
; CHECK-LABEL: testfn:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; CHECK-NEXT: v_add_f64 v[6:7], v[4:5], -v[0:1]
-; CHECK-NEXT: v_add_f64 v[4:5], v[0:1], -v[4:5]
-; CHECK-NEXT: v_add_f64 v[0:1], v[6:7], -v[2:3]
-; CHECK-NEXT: v_add_f64 v[2:3], -v[2:3], v[4:5]
+; CHECK-NEXT: v_add_f64 v[4:5], v[4:5], -v[0:1]
+; CHECK-NEXT: v_add_f64 v[0:1], v[4:5], -v[2:3]
+; CHECK-NEXT: v_add_f64 v[2:3], -v[2:3], -v[4:5]
; CHECK-NEXT: s_setpc_b64 s[30:31]
bb:
%tmp = fsub fast double 0.000000e+00, %arg1
Index: llvm/test/CodeGen/AArch64/arm64-fp.ll
===================================================================
--- llvm/test/CodeGen/AArch64/arm64-fp.ll
+++ llvm/test/CodeGen/AArch64/arm64-fp.ll
@@ -38,9 +38,8 @@
define { double, double } @testfn(double %x, double %y) #0 {
; CHECK-LABEL: testfn:
; CHECK: // %bb.0:
-; CHECK-NEXT: fsub d2, d0, d1
-; CHECK-NEXT: fsub d1, d1, d0
-; CHECK-NEXT: mov v0.16b, v2.16b
+; CHECK-NEXT: fsub d0, d0, d1
+; CHECK-NEXT: fneg d1, d0
; CHECK-NEXT: ret
%sub = fsub fast double %x, %y
%neg = fneg fast double %sub
Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -4688,11 +4688,6 @@
if (OpOpcode == ISD::UNDEF)
return getUNDEF(VT);
- // -(X-Y) -> (Y-X) is unsafe because when X==Y, -0.0 != +0.0
- if ((getTarget().Options.NoSignedZerosFPMath || Flags.hasNoSignedZeros()) &&
- OpOpcode == ISD::FSUB)
- return getNode(ISD::FSUB, DL, VT, Operand.getOperand(1),
- Operand.getOperand(0), Flags);
if (OpOpcode == ISD::FNEG) // --X -> X
return Operand.getOperand(0);
break;
Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -13350,6 +13350,16 @@
if (TLI.isNegatibleForFree(N0, DAG, LegalOperations, ForCodeSize))
return TLI.getNegatedExpression(N0, DAG, LegalOperations, ForCodeSize);
+ // -(X-Y) -> (Y-X) is unsafe because when X==Y, -0.0 != +0.0 FIXME: This is
+ // duplicated in isNegatibleForFree, but isNegatibleForFree doesn't know it
+ // was called from a context with a nsz flag if the input fsub does not.
+ if (N0.getOpcode() == ISD::FSUB &&
+ (DAG.getTarget().Options.NoSignedZerosFPMath ||
+ N->getFlags().hasNoSignedZeros()) && N0.hasOneUse()) {
+ return DAG.getNode(ISD::FSUB, SDLoc(N), VT, N0.getOperand(1),
+ N0.getOperand(0), N->getFlags());
+ }
+
// Transform fneg(bitconvert(x)) -> bitconvert(x ^ sign) to avoid loading
// constant pool values.
if (!TLI.isFNegFree(VT) &&
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D72015.235726.patch
Type: text/x-patch
Size: 3791 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191231/94ee3c02/attachment.bin>
More information about the llvm-commits
mailing list