[SelectionDAG] Remove NoInfsFPMath uses #162788

paperchalice · 2025-10-10T06:31:21Z

Users should use fast-math flags instead.

github-actions · 2025-10-10T10:36:31Z

✅ With the latest revision this PR passed the undef deprecator.

llvmbot · 2025-10-10T11:43:44Z

@llvm/pr-subscribers-llvm-selectiondag
@llvm/pr-subscribers-backend-x86

@llvm/pr-subscribers-backend-amdgpu

Author: None (paperchalice)

Changes

Users should use fast-math flags instead.

Patch is 250.09 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/162788.diff

5 Files Affected:

(modified) llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp (+4-12)
(modified) llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp (+1-1)
(modified) llvm/test/CodeGen/AMDGPU/fma-combine.ll (+1199-814)
(modified) llvm/test/CodeGen/X86/fma_patterns.ll (+1001-860)
(modified) llvm/test/CodeGen/X86/fma_patterns_wide.ll (+678-591)

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index c5c38661f1d71..0aea025530fa7 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -17086,11 +17086,6 @@ static bool isContractableFMUL(const TargetOptions &Options, SDValue N) {
          N->getFlags().hasAllowContract();
 }
 
-// Returns true if `N` can assume no infinities involved in its computation.
-static bool hasNoInfs(const TargetOptions &Options, SDValue N) {
-  return Options.NoInfsFPMath || N->getFlags().hasNoInfs();
-}
-
 /// Try to perform FMA combining on a given FADD node.
 template <class MatchContextClass>
 SDValue DAGCombiner::visitFADDForFMACombine(SDNode *N) {
@@ -17666,7 +17661,7 @@ SDValue DAGCombiner::visitFMULForFMADistributiveCombine(SDNode *N) {
   // The transforms below are incorrect when x == 0 and y == inf, because the
   // intermediate multiplication produces a nan.
   SDValue FAdd = N0.getOpcode() == ISD::FADD ? N0 : N1;
-  if (!hasNoInfs(Options, FAdd))
+  if (!FAdd->getFlags().hasNoInfs())
     return SDValue();
 
   // Floating-point multiply-add without intermediate rounding.
@@ -18343,7 +18338,7 @@ template <class MatchContextClass> SDValue DAGCombiner::visitFMA(SDNode *N) {
       return matcher.getNode(ISD::FMA, DL, VT, NegN0, NegN1, N2);
   }
 
-  if ((Options.NoNaNsFPMath && Options.NoInfsFPMath) ||
+  if ((Options.NoNaNsFPMath && N->getFlags().hasNoInfs()) ||
       (N->getFlags().hasNoNaNs() && N->getFlags().hasNoInfs())) {
     if (N->getFlags().hasNoSignedZeros() ||
         (N2CFP && !N2CFP->isExactlyValue(-0.0))) {
@@ -18533,7 +18528,6 @@ SDValue DAGCombiner::visitFDIV(SDNode *N) {
   SDValue N1 = N->getOperand(1);
   EVT VT = N->getValueType(0);
   SDLoc DL(N);
-  const TargetOptions &Options = DAG.getTarget().Options;
   SDNodeFlags Flags = N->getFlags();
   SelectionDAG::FlagInserter FlagsInserter(DAG, N);
 
@@ -18644,7 +18638,7 @@ SDValue DAGCombiner::visitFDIV(SDNode *N) {
     }
 
     // Fold into a reciprocal estimate and multiply instead of a real divide.
-    if (Options.NoInfsFPMath || Flags.hasNoInfs())
+    if (Flags.hasNoInfs())
       if (SDValue RV = BuildDivEstimate(N0, N1, Flags))
         return RV;
   }
@@ -18721,12 +18715,10 @@ SDValue DAGCombiner::visitFREM(SDNode *N) {
 
 SDValue DAGCombiner::visitFSQRT(SDNode *N) {
   SDNodeFlags Flags = N->getFlags();
-  const TargetOptions &Options = DAG.getTarget().Options;
 
   // Require 'ninf' flag since sqrt(+Inf) = +Inf, but the estimation goes as:
   // sqrt(+Inf) == rsqrt(+Inf) * +Inf = 0 * +Inf = NaN
-  if (!Flags.hasApproximateFuncs() ||
-      (!Options.NoInfsFPMath && !Flags.hasNoInfs()))
+  if (!Flags.hasApproximateFuncs() || !Flags.hasNoInfs())
     return SDValue();
 
   SDValue N0 = N->getOperand(0);
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 6ea2e2708c162..3d963103d7469 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -5771,7 +5771,7 @@ bool SelectionDAG::canCreateUndefOrPoison(SDValue Op, const APInt &DemandedElts,
       return true;
 
     const TargetOptions &Options = getTarget().Options;
-    return Options.NoNaNsFPMath || Options.NoInfsFPMath;
+    return Options.NoNaNsFPMath || Op->getFlags().hasNoInfs();
   }
 
   case ISD::OR:
diff --git a/llvm/test/CodeGen/AMDGPU/fma-combine.ll b/llvm/test/CodeGen/AMDGPU/fma-combine.ll
index d7cf411da0ccb..8fc6904f5009c 100644
--- a/llvm/test/CodeGen/AMDGPU/fma-combine.ll
+++ b/llvm/test/CodeGen/AMDGPU/fma-combine.ll
@@ -1,9 +1,9 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
-; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tahiti -denormal-fp-math-f32=preserve-sign < %s | FileCheck -enable-var-scope -check-prefixes=SI,SI-NOFMA %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=verde -denormal-fp-math-f32=preserve-sign < %s | FileCheck -enable-var-scope -check-prefixes=SI,SI-NOFMA %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tahiti -denormal-fp-math-f32=ieee  -enable-no-infs-fp-math < %s | FileCheck -enable-var-scope -check-prefixes=SI,SI-FMA %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tahiti -denormal-fp-math-f32=preserve-sign < %s | FileCheck -enable-var-scope -check-prefixes=SI,SI-NOFMA,TAHITI %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=verde -denormal-fp-math-f32=preserve-sign < %s | FileCheck -enable-var-scope -check-prefixes=SI,SI-NOFMA,VERDE %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tahiti -denormal-fp-math-f32=ieee < %s | FileCheck -enable-var-scope -check-prefixes=SI,SI-FMA %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1100 -denormal-fp-math-f32=preserve-sign  < %s | FileCheck -enable-var-scope -check-prefixes=GFX11,GFX11-NOFMA %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1100 -denormal-fp-math-f32=ieee -enable-no-infs-fp-math < %s | FileCheck -enable-var-scope -check-prefixes=GFX11,GFX11-FMA %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx1100 -denormal-fp-math-f32=ieee < %s | FileCheck -enable-var-scope -check-prefixes=GFX11,GFX11-FMA %s
 
 ; Note: The SI-FMA conversions of type x * (y + 1) --> x * y + x would be
 ; beneficial even without fp32 denormals, but they do require no-infs-fp-math
@@ -648,53 +648,53 @@ define amdgpu_kernel void @combine_to_fma_fsub_2_f64_2uses_mul(ptr addrspace(1)
 
 ; fold (fsub (fma x, y, (fmul u, v)), z) -> (fma x, y (fma u, v, (fneg z)))
 define amdgpu_kernel void @aggressive_combine_to_fma_fsub_0_f64(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) #1 {
-; SI-FMA-LABEL: aggressive_combine_to_fma_fsub_0_f64:
-; SI-FMA:       ; %bb.0:
-; SI-FMA-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
-; SI-FMA-NEXT:    s_mov_b32 s7, 0xf000
-; SI-FMA-NEXT:    s_mov_b32 s6, 0
-; SI-FMA-NEXT:    v_lshlrev_b32_e32 v0, 3, v0
-; SI-FMA-NEXT:    v_mov_b32_e32 v1, 0
-; SI-FMA-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-FMA-NEXT:    s_mov_b64 s[4:5], s[2:3]
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[2:3], v[0:1], s[4:7], 0 addr64 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[4:5], v[0:1], s[4:7], 0 addr64 offset:8 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[6:7], v[0:1], s[4:7], 0 addr64 offset:16 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[8:9], v[0:1], s[4:7], 0 addr64 offset:24 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[10:11], v[0:1], s[4:7], 0 addr64 offset:32 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    s_mov_b64 s[2:3], s[6:7]
-; SI-FMA-NEXT:    v_fma_f64 v[6:7], v[8:9], v[10:11], -v[6:7]
-; SI-FMA-NEXT:    v_fma_f64 v[2:3], v[2:3], v[4:5], v[6:7]
-; SI-FMA-NEXT:    buffer_store_dwordx2 v[2:3], v[0:1], s[0:3], 0 addr64
-; SI-FMA-NEXT:    s_endpgm
+; SI-LABEL: aggressive_combine_to_fma_fsub_0_f64:
+; SI:       ; %bb.0:
+; SI-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
+; SI-NEXT:    s_mov_b32 s7, 0xf000
+; SI-NEXT:    s_mov_b32 s6, 0
+; SI-NEXT:    v_lshlrev_b32_e32 v0, 3, v0
+; SI-NEXT:    v_mov_b32_e32 v1, 0
+; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b64 s[4:5], s[2:3]
+; SI-NEXT:    buffer_load_dwordx2 v[2:3], v[0:1], s[4:7], 0 addr64 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[4:5], v[0:1], s[4:7], 0 addr64 offset:8 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[6:7], v[0:1], s[4:7], 0 addr64 offset:16 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[8:9], v[0:1], s[4:7], 0 addr64 offset:24 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[10:11], v[0:1], s[4:7], 0 addr64 offset:32 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    s_mov_b64 s[2:3], s[6:7]
+; SI-NEXT:    v_fma_f64 v[6:7], v[8:9], v[10:11], -v[6:7]
+; SI-NEXT:    v_fma_f64 v[2:3], v[2:3], v[4:5], v[6:7]
+; SI-NEXT:    buffer_store_dwordx2 v[2:3], v[0:1], s[0:3], 0 addr64
+; SI-NEXT:    s_endpgm
 ;
-; GFX11-FMA-LABEL: aggressive_combine_to_fma_fsub_0_f64:
-; GFX11-FMA:       ; %bb.0:
-; GFX11-FMA-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
-; GFX11-FMA-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
-; GFX11-FMA-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-FMA-NEXT:    v_lshlrev_b32_e32 v10, 3, v0
-; GFX11-FMA-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[0:1], v10, s[2:3] glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[2:3], v10, s[2:3] offset:8 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[4:5], v10, s[2:3] offset:16 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[6:7], v10, s[2:3] offset:24 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[8:9], v10, s[2:3] offset:32 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    v_fma_f64 v[4:5], v[6:7], v[8:9], -v[4:5]
-; GFX11-FMA-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-FMA-NEXT:    v_fma_f64 v[0:1], v[0:1], v[2:3], v[4:5]
-; GFX11-FMA-NEXT:    global_store_b64 v10, v[0:1], s[0:1]
-; GFX11-FMA-NEXT:    s_endpgm
+; GFX11-LABEL: aggressive_combine_to_fma_fsub_0_f64:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT:    v_lshlrev_b32_e32 v10, 3, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[0:1], v10, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[2:3], v10, s[2:3] offset:8 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[4:5], v10, s[2:3] offset:16 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[6:7], v10, s[2:3] offset:24 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[8:9], v10, s[2:3] offset:32 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_fma_f64 v[4:5], v[6:7], v[8:9], -v[4:5]
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT:    v_fma_f64 v[0:1], v[0:1], v[2:3], v[4:5]
+; GFX11-NEXT:    global_store_b64 v10, v[0:1], s[0:1]
+; GFX11-NEXT:    s_endpgm
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %gep.0 = getelementptr double, ptr addrspace(1) %in, i32 %tid
   %gep.1 = getelementptr double, ptr addrspace(1) %gep.0, i32 1
@@ -718,55 +718,55 @@ define amdgpu_kernel void @aggressive_combine_to_fma_fsub_0_f64(ptr addrspace(1)
 }
 
 define amdgpu_kernel void @no_aggressive_combine_to_fma_fsub_0_f64(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) #1 {
-; SI-NOFMA-LABEL: no_aggressive_combine_to_fma_fsub_0_f64:
-; SI-NOFMA:       ; %bb.0:
-; SI-NOFMA-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
-; SI-NOFMA-NEXT:    s_mov_b32 s7, 0xf000
-; SI-NOFMA-NEXT:    s_mov_b32 s6, 0
-; SI-NOFMA-NEXT:    v_lshlrev_b32_e32 v0, 3, v0
-; SI-NOFMA-NEXT:    v_mov_b32_e32 v1, 0
-; SI-NOFMA-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NOFMA-NEXT:    s_mov_b64 s[4:5], s[2:3]
-; SI-NOFMA-NEXT:    buffer_load_dwordx2 v[2:3], v[0:1], s[4:7], 0 addr64 glc
-; SI-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-NOFMA-NEXT:    buffer_load_dwordx2 v[4:5], v[0:1], s[4:7], 0 addr64 offset:8 glc
-; SI-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-NOFMA-NEXT:    buffer_load_dwordx2 v[6:7], v[0:1], s[4:7], 0 addr64 offset:16 glc
-; SI-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-NOFMA-NEXT:    buffer_load_dwordx2 v[8:9], v[0:1], s[4:7], 0 addr64 offset:24 glc
-; SI-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-NOFMA-NEXT:    buffer_load_dwordx2 v[10:11], v[0:1], s[4:7], 0 addr64 offset:32 glc
-; SI-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-NOFMA-NEXT:    s_mov_b64 s[2:3], s[6:7]
-; SI-NOFMA-NEXT:    v_mul_f64 v[8:9], v[8:9], v[10:11]
-; SI-NOFMA-NEXT:    v_fma_f64 v[2:3], v[2:3], v[4:5], v[8:9]
-; SI-NOFMA-NEXT:    v_add_f64 v[2:3], v[2:3], -v[6:7]
-; SI-NOFMA-NEXT:    buffer_store_dwordx2 v[2:3], v[0:1], s[0:3], 0 addr64
-; SI-NOFMA-NEXT:    s_endpgm
+; SI-LABEL: no_aggressive_combine_to_fma_fsub_0_f64:
+; SI:       ; %bb.0:
+; SI-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
+; SI-NEXT:    s_mov_b32 s7, 0xf000
+; SI-NEXT:    s_mov_b32 s6, 0
+; SI-NEXT:    v_lshlrev_b32_e32 v0, 3, v0
+; SI-NEXT:    v_mov_b32_e32 v1, 0
+; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b64 s[4:5], s[2:3]
+; SI-NEXT:    buffer_load_dwordx2 v[2:3], v[0:1], s[4:7], 0 addr64 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[4:5], v[0:1], s[4:7], 0 addr64 offset:8 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[6:7], v[0:1], s[4:7], 0 addr64 offset:16 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[8:9], v[0:1], s[4:7], 0 addr64 offset:24 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[10:11], v[0:1], s[4:7], 0 addr64 offset:32 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    s_mov_b64 s[2:3], s[6:7]
+; SI-NEXT:    v_mul_f64 v[8:9], v[8:9], v[10:11]
+; SI-NEXT:    v_fma_f64 v[2:3], v[2:3], v[4:5], v[8:9]
+; SI-NEXT:    v_add_f64 v[2:3], v[2:3], -v[6:7]
+; SI-NEXT:    buffer_store_dwordx2 v[2:3], v[0:1], s[0:3], 0 addr64
+; SI-NEXT:    s_endpgm
 ;
-; GFX11-NOFMA-LABEL: no_aggressive_combine_to_fma_fsub_0_f64:
-; GFX11-NOFMA:       ; %bb.0:
-; GFX11-NOFMA-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
-; GFX11-NOFMA-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
-; GFX11-NOFMA-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NOFMA-NEXT:    v_lshlrev_b32_e32 v10, 3, v0
-; GFX11-NOFMA-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-NOFMA-NEXT:    global_load_b64 v[0:1], v10, s[2:3] glc dlc
-; GFX11-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NOFMA-NEXT:    global_load_b64 v[2:3], v10, s[2:3] offset:8 glc dlc
-; GFX11-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NOFMA-NEXT:    global_load_b64 v[4:5], v10, s[2:3] offset:16 glc dlc
-; GFX11-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NOFMA-NEXT:    global_load_b64 v[6:7], v10, s[2:3] offset:24 glc dlc
-; GFX11-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NOFMA-NEXT:    global_load_b64 v[8:9], v10, s[2:3] offset:32 glc dlc
-; GFX11-NOFMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NOFMA-NEXT:    v_mul_f64 v[6:7], v[6:7], v[8:9]
-; GFX11-NOFMA-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NOFMA-NEXT:    v_fma_f64 v[0:1], v[0:1], v[2:3], v[6:7]
-; GFX11-NOFMA-NEXT:    v_add_f64 v[0:1], v[0:1], -v[4:5]
-; GFX11-NOFMA-NEXT:    global_store_b64 v10, v[0:1], s[0:1]
-; GFX11-NOFMA-NEXT:    s_endpgm
+; GFX11-LABEL: no_aggressive_combine_to_fma_fsub_0_f64:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT:    v_lshlrev_b32_e32 v10, 3, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[0:1], v10, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[2:3], v10, s[2:3] offset:8 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[4:5], v10, s[2:3] offset:16 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[6:7], v10, s[2:3] offset:24 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b64 v[8:9], v10, s[2:3] offset:32 glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_mul_f64 v[6:7], v[6:7], v[8:9]
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-NEXT:    v_fma_f64 v[0:1], v[0:1], v[2:3], v[6:7]
+; GFX11-NEXT:    v_add_f64 v[0:1], v[0:1], -v[4:5]
+; GFX11-NEXT:    global_store_b64 v10, v[0:1], s[0:1]
+; GFX11-NEXT:    s_endpgm
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %gep.0 = getelementptr double, ptr addrspace(1) %in, i32 %tid
   %gep.1 = getelementptr double, ptr addrspace(1) %gep.0, i32 1
@@ -792,53 +792,53 @@ define amdgpu_kernel void @no_aggressive_combine_to_fma_fsub_0_f64(ptr addrspace
 ; fold (fsub x, (fma y, z, (fmul u, v)))
 ;   -> (fma (fneg y), z, (fma (fneg u), v, x))
 define amdgpu_kernel void @aggressive_combine_to_fma_fsub_1_f64(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) #1 {
-; SI-FMA-LABEL: aggressive_combine_to_fma_fsub_1_f64:
-; SI-FMA:       ; %bb.0:
-; SI-FMA-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
-; SI-FMA-NEXT:    s_mov_b32 s7, 0xf000
-; SI-FMA-NEXT:    s_mov_b32 s6, 0
-; SI-FMA-NEXT:    v_lshlrev_b32_e32 v0, 3, v0
-; SI-FMA-NEXT:    v_mov_b32_e32 v1, 0
-; SI-FMA-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-FMA-NEXT:    s_mov_b64 s[4:5], s[2:3]
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[2:3], v[0:1], s[4:7], 0 addr64 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[4:5], v[0:1], s[4:7], 0 addr64 offset:8 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[6:7], v[0:1], s[4:7], 0 addr64 offset:16 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[8:9], v[0:1], s[4:7], 0 addr64 offset:24 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    buffer_load_dwordx2 v[10:11], v[0:1], s[4:7], 0 addr64 offset:32 glc
-; SI-FMA-NEXT:    s_waitcnt vmcnt(0)
-; SI-FMA-NEXT:    s_mov_b64 s[2:3], s[6:7]
-; SI-FMA-NEXT:    v_fma_f64 v[2:3], -v[8:9], v[10:11], v[2:3]
-; SI-FMA-NEXT:    v_fma_f64 v[2:3], -v[4:5], v[6:7], v[2:3]
-; SI-FMA-NEXT:    buffer_store_dwordx2 v[2:3], v[0:1], s[0:3], 0 addr64
-; SI-FMA-NEXT:    s_endpgm
+; SI-LABEL: aggressive_combine_to_fma_fsub_1_f64:
+; SI:       ; %bb.0:
+; SI-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
+; SI-NEXT:    s_mov_b32 s7, 0xf000
+; SI-NEXT:    s_mov_b32 s6, 0
+; SI-NEXT:    v_lshlrev_b32_e32 v0, 3, v0
+; SI-NEXT:    v_mov_b32_e32 v1, 0
+; SI-NEXT:    s_waitcnt lgkmcnt(0)
+; SI-NEXT:    s_mov_b64 s[4:5], s[2:3]
+; SI-NEXT:    buffer_load_dwordx2 v[2:3], v[0:1], s[4:7], 0 addr64 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[4:5], v[0:1], s[4:7], 0 addr64 offset:8 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[6:7], v[0:1], s[4:7], 0 addr64 offset:16 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[8:9], v[0:1], s[4:7], 0 addr64 offset:24 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    buffer_load_dwordx2 v[10:11], v[0:1], s[4:7], 0 addr64 offset:32 glc
+; SI-NEXT:    s_waitcnt vmcnt(0)
+; SI-NEXT:    s_mov_b64 s[2:3], s[6:7]
+; SI-NEXT:    v_fma_f64 v[2:3], -v[8:9], v[10:11], v[2:3]
+; SI-NEXT:    v_fma_f64 v[2:3], -v[4:5], v[6:7], v[2:3]
+; SI-NEXT:    buffer_store_dwordx2 v[2:3], v[0:1], s[0:3], 0 addr64
+; SI-NEXT:    s_endpgm
 ;
-; GFX11-FMA-LABEL: aggressive_combine_to_fma_fsub_1_f64:
-; GFX11-FMA:       ; %bb.0:
-; GFX11-FMA-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
-; GFX11-FMA-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
-; GFX11-FMA-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-FMA-NEXT:    v_lshlrev_b32_e32 v10, 3, v0
-; GFX11-FMA-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[0:1], v10, s[2:3] glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[2:3], v10, s[2:3] offset:8 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[4:5], v10, s[2:3] offset:16 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[6:7], v10, s[2:3] offset:24 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    global_load_b64 v[8:9], v10, s[2:3] offset:32 glc dlc
-; GFX11-FMA-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-FMA-NEXT:    v_fma_f64 v[0:1], -v[6:7], v[8:9], v[0:1]
-; GFX11-FMA-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-FMA-NEXT:    v_fma_f64 v[0:1], -v[2:3], v[4:5], v[0:1]
-; GFX11-FMA-NEXT:    global_store_b64 v10, v[0:1], s[0:1]
-; GFX11-FMA-NEXT:    s_endpgm
+; GFX11-LABEL: aggressive_combine_to_fma_fsub_1_f64:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT:    v_lshlrev_...
[truncated]

arsenm · 2025-10-10T14:01:33Z

llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp


    const TargetOptions &Options = getTarget().Options;
-    return Options.NoNaNsFPMath || Options.NoInfsFPMath;
+    return Options.NoNaNsFPMath || Op->getFlags().hasNoInfs();


This should have been covered by the hasPoisonGeneratingFlags above

paperchalice force-pushed the sdag-ninf branch 2 times, most recently from 78298c0 to fa27d74 Compare October 10, 2025 06:47

[SelectionDAG] Remove NoInfsFPMath uses

8618eed

paperchalice force-pushed the sdag-ninf branch from fa27d74 to 8618eed Compare October 10, 2025 09:48

paperchalice added 2 commits October 10, 2025 17:59

regenerate fma-combine.ll

1721b2d

fix tests

87ed258

use poison instead of undef

189805a

paperchalice force-pushed the sdag-ninf branch from 477e206 to 189805a Compare October 10, 2025 11:00

paperchalice marked this pull request as ready for review October 10, 2025 11:43

llvmbot added backend:AMDGPU backend:X86 llvm:SelectionDAG SelectionDAGISel as well labels Oct 10, 2025

paperchalice requested review from RKSimon and arsenm October 10, 2025 11:43

paperchalice added the floating-point Floating-point math label Oct 10, 2025

arsenm reviewed Oct 10, 2025

View reviewed changes

remove hasPoisonGeneratingFlags covered check

2438adc

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[SelectionDAG] Remove NoInfsFPMath uses #162788

[SelectionDAG] Remove NoInfsFPMath uses #162788

paperchalice commented Oct 10, 2025 •

edited

Loading

Uh oh!

github-actions bot commented Oct 10, 2025 •

edited

Loading

Uh oh!

llvmbot commented Oct 10, 2025 •

edited

Loading

Uh oh!

arsenm Oct 10, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[SelectionDAG] Remove NoInfsFPMath uses #162788

Are you sure you want to change the base?

[SelectionDAG] Remove NoInfsFPMath uses #162788

Conversation

paperchalice commented Oct 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Oct 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

llvmbot commented Oct 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

arsenm Oct 10, 2025

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

paperchalice commented Oct 10, 2025 •

edited

Loading

github-actions bot commented Oct 10, 2025 •

edited

Loading

llvmbot commented Oct 10, 2025 •

edited

Loading