From f63366261bc52f6c4daac49019299b4b22a8abec Mon Sep 17 00:00:00 2001 From: David Green Date: Mon, 16 Jun 2025 08:06:46 +0100 Subject: [PATCH 1/2] [GlobalISel] fdiv to fmul transform This is a port of the SDAG DAGCombiner::combineRepeatedFPDivisors combine that looks like multiple fdiv operations with the same divisor and converts them to a single reciprocal fdiv and multiple fmuls. It is currently a fairly faithful port, with some additions to make sure that the newly created fdiv dominates all new uses. Compared to the SDAG version it also drops some logic about splat uses which assumes no vector fdivs and some logic about x/sqrt(x) which does not yet apply to GISel. --- .../llvm/CodeGen/GlobalISel/CombinerHelper.h | 4 + .../include/llvm/Target/GlobalISel/Combine.td | 11 +- .../lib/CodeGen/GlobalISel/CombinerHelper.cpp | 70 ++++++++++ llvm/test/CodeGen/AArch64/fdiv-combine.ll | 125 ++++++------------ 4 files changed, 126 insertions(+), 84 deletions(-) diff --git a/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h b/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h index c15263e0b06f8..f5a8ed9edac16 100644 --- a/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h +++ b/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h @@ -809,6 +809,10 @@ class CombinerHelper { bool matchCombineFMinMaxNaN(MachineInstr &MI, unsigned &Info) const; + bool matchRepeatedFPDivisor(MachineInstr &MI, + SmallVector &MatchInfo) const; + void applyRepeatedFPDivisor(SmallVector &MatchInfo) const; + /// Transform G_ADD(x, G_SUB(y, x)) to y. /// Transform G_ADD(G_SUB(y, x), x) to y. bool matchAddSubSameReg(MachineInstr &MI, Register &Src) const; diff --git a/llvm/include/llvm/Target/GlobalISel/Combine.td b/llvm/include/llvm/Target/GlobalISel/Combine.td index efd88524a159e..1447b293146db 100644 --- a/llvm/include/llvm/Target/GlobalISel/Combine.td +++ b/llvm/include/llvm/Target/GlobalISel/Combine.td @@ -211,6 +211,7 @@ def constantfp_matchinfo : GIDefMatchData<"ConstantFP*">; def build_fn_matchinfo : GIDefMatchData<"std::function">; def unsigned_matchinfo: GIDefMatchData<"unsigned">; +def mi_vector_matchinfo : GIDefMatchData<"SmallVector">; def copy_prop : GICombineRule< (defs root:$d), @@ -1327,6 +1328,14 @@ def combine_minmax_nan: GICombineRule< [{ return Helper.matchCombineFMinMaxNaN(*${root}, ${info}); }]), (apply [{ Helper.replaceSingleDefInstWithOperand(*${root}, ${info}); }])>; +// Combine multiple FDIVs with the same divisor into multiple FMULs by the +// reciprocal. +def fdiv_repeated_divison: GICombineRule< + (defs root:$root, mi_vector_matchinfo:$matchinfo), + (match (G_FDIV $dst, $src1, $src2):$root, + [{ return Helper.matchRepeatedFPDivisor(*${root}, ${matchinfo}); }]), + (apply [{ Helper.applyRepeatedFPDivisor(${matchinfo}); }])>; + // Transform (add x, (sub y, x)) -> y // Transform (add (sub y, x), x) -> y def add_sub_reg_frags : GICombinePatFrag< @@ -2051,7 +2060,7 @@ def all_combines : GICombineGroup<[integer_reassoc_combines, trivial_combines, constant_fold_cast_op, fabs_fneg_fold, intdiv_combines, mulh_combines, redundant_neg_operands, and_or_disjoint_mask, fma_combines, fold_binop_into_select, - sub_add_reg, select_to_minmax, + sub_add_reg, select_to_minmax, fdiv_repeated_divison, fsub_to_fneg, commute_constant_to_rhs, match_ands, match_ors, simplify_neg_minmax, combine_concat_vector, sext_trunc, zext_trunc, prefer_sign_combines, shuffle_combines, diff --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp index b1e851183de0d..a50641f219fbc 100644 --- a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp +++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp @@ -6389,6 +6389,76 @@ bool CombinerHelper::matchCombineFMinMaxNaN(MachineInstr &MI, return MatchNaN(1) || MatchNaN(2); } +// Combine multiple FDIVs with the same divisor into multiple FMULs by the +// reciprocal. +// E.g., (a / D; b / D;) -> (recip = 1.0 / D; a * recip; b * recip) +bool CombinerHelper::matchRepeatedFPDivisor( + MachineInstr &MI, SmallVector &MatchInfo) const { + assert(MI.getOpcode() == TargetOpcode::G_FDIV); + auto *MF = MI.getMF(); + const TargetOptions &Options = MF->getTarget().Options; + + Register X = MI.getOperand(1).getReg(); + Register Y = MI.getOperand(2).getReg(); + + bool UnsafeMath = Options.UnsafeFPMath; + if (!UnsafeMath && !MI.getFlag(MachineInstr::MIFlag::FmArcp)) + return false; + + // Skip if current node is a reciprocal/fneg-reciprocal. + auto N0CFP = isConstantOrConstantSplatVectorFP(*MRI.getVRegDef(X), MRI); + if (N0CFP && (N0CFP->isExactlyValue(1.0) || N0CFP->isExactlyValue(-1.0))) + return false; + + // Exit early if the target does not want this transform or if there can't + // possibly be enough uses of the divisor to make the transform worthwhile. + unsigned MinUses = getTargetLowering().combineRepeatedFPDivisors(); + + if (!MinUses) + return false; + + // Find all FDIV users of the same divisor. Use a set because duplicates may + // be present in the user list. For the moment we limit all instructions to a + // single BB and use the first Instr in MatchInfo as the dominating position. + MatchInfo.push_back(&MI); + for (auto &U : MRI.use_nodbg_instructions(Y)) { + if (&U == &MI || U.getParent() != MI.getParent()) + continue; + if (U.getOpcode() == TargetOpcode::G_FDIV && + U.getOperand(2).getReg() == Y) { + // This division is eligible for optimization only if global unsafe math + // is enabled or if this division allows reciprocal formation. + if (UnsafeMath || U.getFlag(MachineInstr::MIFlag::FmArcp)) { + MatchInfo.push_back(&U); + if (dominates(U, *MatchInfo[0])) + std::swap(MatchInfo[0], MatchInfo.back()); + } + } + } + + // Now that we have the actual number of divisor uses, make sure it meets + // the minimum threshold specified by the target. + return MatchInfo.size() >= MinUses; +} + +void CombinerHelper::applyRepeatedFPDivisor( + SmallVector &MatchInfo) const { + // Generate the new div at the position of the first instruction, that we have + // ensured will dominate all other instructions. + Builder.setInsertPt(*MatchInfo[0]->getParent(), MatchInfo[0]); + LLT Ty = MRI.getType(MatchInfo[0]->getOperand(0).getReg()); + auto Div = Builder.buildFDiv(Ty, Builder.buildFConstant(Ty, 1.0), + MatchInfo[0]->getOperand(2).getReg()); + + // Replace all found div's with fmul instructions. + for (MachineInstr *MI : MatchInfo) { + Builder.setInsertPt(*MI->getParent(), MI); + Builder.buildFMul(MI->getOperand(0).getReg(), MI->getOperand(1).getReg(), + Div->getOperand(0).getReg()); + MI->eraseFromParent(); + } +} + bool CombinerHelper::matchAddSubSameReg(MachineInstr &MI, Register &Src) const { assert(MI.getOpcode() == TargetOpcode::G_ADD && "Expected a G_ADD"); Register LHS = MI.getOperand(1).getReg(); diff --git a/llvm/test/CodeGen/AArch64/fdiv-combine.ll b/llvm/test/CodeGen/AArch64/fdiv-combine.ll index d8f7f0a306684..e566e54a2964a 100644 --- a/llvm/test/CodeGen/AArch64/fdiv-combine.ll +++ b/llvm/test/CodeGen/AArch64/fdiv-combine.ll @@ -12,22 +12,14 @@ ; => ; recip = 1.0 / D; a * recip; b * recip; c * recip; define void @three_fdiv_float(float %D, float %a, float %b, float %c) #0 { -; CHECK-SD-LABEL: three_fdiv_float: -; CHECK-SD: // %bb.0: -; CHECK-SD-NEXT: fmov s4, #1.00000000 -; CHECK-SD-NEXT: fdiv s4, s4, s0 -; CHECK-SD-NEXT: fmul s0, s1, s4 -; CHECK-SD-NEXT: fmul s1, s2, s4 -; CHECK-SD-NEXT: fmul s2, s3, s4 -; CHECK-SD-NEXT: b foo_3f -; -; CHECK-GI-LABEL: three_fdiv_float: -; CHECK-GI: // %bb.0: -; CHECK-GI-NEXT: fdiv s4, s1, s0 -; CHECK-GI-NEXT: fdiv s1, s2, s0 -; CHECK-GI-NEXT: fdiv s2, s3, s0 -; CHECK-GI-NEXT: fmov s0, s4 -; CHECK-GI-NEXT: b foo_3f +; CHECK-LABEL: three_fdiv_float: +; CHECK: // %bb.0: +; CHECK-NEXT: fmov s4, #1.00000000 +; CHECK-NEXT: fdiv s4, s4, s0 +; CHECK-NEXT: fmul s0, s1, s4 +; CHECK-NEXT: fmul s1, s2, s4 +; CHECK-NEXT: fmul s2, s3, s4 +; CHECK-NEXT: b foo_3f %div = fdiv float %a, %D %div1 = fdiv float %b, %D %div2 = fdiv float %c, %D @@ -36,22 +28,14 @@ define void @three_fdiv_float(float %D, float %a, float %b, float %c) #0 { } define void @three_fdiv_double(double %D, double %a, double %b, double %c) #0 { -; CHECK-SD-LABEL: three_fdiv_double: -; CHECK-SD: // %bb.0: -; CHECK-SD-NEXT: fmov d4, #1.00000000 -; CHECK-SD-NEXT: fdiv d4, d4, d0 -; CHECK-SD-NEXT: fmul d0, d1, d4 -; CHECK-SD-NEXT: fmul d1, d2, d4 -; CHECK-SD-NEXT: fmul d2, d3, d4 -; CHECK-SD-NEXT: b foo_3d -; -; CHECK-GI-LABEL: three_fdiv_double: -; CHECK-GI: // %bb.0: -; CHECK-GI-NEXT: fdiv d4, d1, d0 -; CHECK-GI-NEXT: fdiv d1, d2, d0 -; CHECK-GI-NEXT: fdiv d2, d3, d0 -; CHECK-GI-NEXT: fmov d0, d4 -; CHECK-GI-NEXT: b foo_3d +; CHECK-LABEL: three_fdiv_double: +; CHECK: // %bb.0: +; CHECK-NEXT: fmov d4, #1.00000000 +; CHECK-NEXT: fdiv d4, d4, d0 +; CHECK-NEXT: fmul d0, d1, d4 +; CHECK-NEXT: fmul d1, d2, d4 +; CHECK-NEXT: fmul d2, d3, d4 +; CHECK-NEXT: b foo_3d %div = fdiv double %a, %D %div1 = fdiv double %b, %D %div2 = fdiv double %c, %D @@ -60,22 +44,14 @@ define void @three_fdiv_double(double %D, double %a, double %b, double %c) #0 { } define void @three_fdiv_4xfloat(<4 x float> %D, <4 x float> %a, <4 x float> %b, <4 x float> %c) #0 { -; CHECK-SD-LABEL: three_fdiv_4xfloat: -; CHECK-SD: // %bb.0: -; CHECK-SD-NEXT: fmov v4.4s, #1.00000000 -; CHECK-SD-NEXT: fdiv v4.4s, v4.4s, v0.4s -; CHECK-SD-NEXT: fmul v0.4s, v1.4s, v4.4s -; CHECK-SD-NEXT: fmul v1.4s, v2.4s, v4.4s -; CHECK-SD-NEXT: fmul v2.4s, v3.4s, v4.4s -; CHECK-SD-NEXT: b foo_3_4xf -; -; CHECK-GI-LABEL: three_fdiv_4xfloat: -; CHECK-GI: // %bb.0: -; CHECK-GI-NEXT: fdiv v4.4s, v1.4s, v0.4s -; CHECK-GI-NEXT: fdiv v1.4s, v2.4s, v0.4s -; CHECK-GI-NEXT: fdiv v2.4s, v3.4s, v0.4s -; CHECK-GI-NEXT: mov v0.16b, v4.16b -; CHECK-GI-NEXT: b foo_3_4xf +; CHECK-LABEL: three_fdiv_4xfloat: +; CHECK: // %bb.0: +; CHECK-NEXT: fmov v4.4s, #1.00000000 +; CHECK-NEXT: fdiv v4.4s, v4.4s, v0.4s +; CHECK-NEXT: fmul v0.4s, v1.4s, v4.4s +; CHECK-NEXT: fmul v1.4s, v2.4s, v4.4s +; CHECK-NEXT: fmul v2.4s, v3.4s, v4.4s +; CHECK-NEXT: b foo_3_4xf %div = fdiv <4 x float> %a, %D %div1 = fdiv <4 x float> %b, %D %div2 = fdiv <4 x float> %c, %D @@ -84,22 +60,14 @@ define void @three_fdiv_4xfloat(<4 x float> %D, <4 x float> %a, <4 x float> %b, } define void @three_fdiv_2xdouble(<2 x double> %D, <2 x double> %a, <2 x double> %b, <2 x double> %c) #0 { -; CHECK-SD-LABEL: three_fdiv_2xdouble: -; CHECK-SD: // %bb.0: -; CHECK-SD-NEXT: fmov v4.2d, #1.00000000 -; CHECK-SD-NEXT: fdiv v4.2d, v4.2d, v0.2d -; CHECK-SD-NEXT: fmul v0.2d, v1.2d, v4.2d -; CHECK-SD-NEXT: fmul v1.2d, v2.2d, v4.2d -; CHECK-SD-NEXT: fmul v2.2d, v3.2d, v4.2d -; CHECK-SD-NEXT: b foo_3_2xd -; -; CHECK-GI-LABEL: three_fdiv_2xdouble: -; CHECK-GI: // %bb.0: -; CHECK-GI-NEXT: fdiv v4.2d, v1.2d, v0.2d -; CHECK-GI-NEXT: fdiv v1.2d, v2.2d, v0.2d -; CHECK-GI-NEXT: fdiv v2.2d, v3.2d, v0.2d -; CHECK-GI-NEXT: mov v0.16b, v4.16b -; CHECK-GI-NEXT: b foo_3_2xd +; CHECK-LABEL: three_fdiv_2xdouble: +; CHECK: // %bb.0: +; CHECK-NEXT: fmov v4.2d, #1.00000000 +; CHECK-NEXT: fdiv v4.2d, v4.2d, v0.2d +; CHECK-NEXT: fmul v0.2d, v1.2d, v4.2d +; CHECK-NEXT: fmul v1.2d, v2.2d, v4.2d +; CHECK-NEXT: fmul v2.2d, v3.2d, v4.2d +; CHECK-NEXT: b foo_3_2xd %div = fdiv <2 x double> %a, %D %div1 = fdiv <2 x double> %b, %D %div2 = fdiv <2 x double> %c, %D @@ -136,25 +104,16 @@ define void @two_fdiv_double(double %D, double %a, double %b) #0 { } define void @splat_three_fdiv_4xfloat(float %D, <4 x float> %a, <4 x float> %b, <4 x float> %c) #0 { -; CHECK-SD-LABEL: splat_three_fdiv_4xfloat: -; CHECK-SD: // %bb.0: -; CHECK-SD-NEXT: // kill: def $s0 killed $s0 def $q0 -; CHECK-SD-NEXT: fmov v4.4s, #1.00000000 -; CHECK-SD-NEXT: dup v0.4s, v0.s[0] -; CHECK-SD-NEXT: fdiv v4.4s, v4.4s, v0.4s -; CHECK-SD-NEXT: fmul v0.4s, v1.4s, v4.4s -; CHECK-SD-NEXT: fmul v1.4s, v2.4s, v4.4s -; CHECK-SD-NEXT: fmul v2.4s, v3.4s, v4.4s -; CHECK-SD-NEXT: b foo_3_4xf -; -; CHECK-GI-LABEL: splat_three_fdiv_4xfloat: -; CHECK-GI: // %bb.0: -; CHECK-GI-NEXT: // kill: def $s0 killed $s0 def $q0 -; CHECK-GI-NEXT: dup v4.4s, v0.s[0] -; CHECK-GI-NEXT: fdiv v0.4s, v1.4s, v4.4s -; CHECK-GI-NEXT: fdiv v1.4s, v2.4s, v4.4s -; CHECK-GI-NEXT: fdiv v2.4s, v3.4s, v4.4s -; CHECK-GI-NEXT: b foo_3_4xf +; CHECK-LABEL: splat_three_fdiv_4xfloat: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0 +; CHECK-NEXT: fmov v4.4s, #1.00000000 +; CHECK-NEXT: dup v0.4s, v0.s[0] +; CHECK-NEXT: fdiv v4.4s, v4.4s, v0.4s +; CHECK-NEXT: fmul v0.4s, v1.4s, v4.4s +; CHECK-NEXT: fmul v1.4s, v2.4s, v4.4s +; CHECK-NEXT: fmul v2.4s, v3.4s, v4.4s +; CHECK-NEXT: b foo_3_4xf %D.ins = insertelement <4 x float> poison, float %D, i64 0 %splat = shufflevector <4 x float> %D.ins, <4 x float> poison, <4 x i32> zeroinitializer %div = fdiv <4 x float> %a, %splat From 0d0182a02aba213dd889436c17c3613233ba026b Mon Sep 17 00:00:00 2001 From: David Green Date: Tue, 17 Jun 2025 08:09:51 +0100 Subject: [PATCH 2/2] Fixups and an extra test case. --- .../lib/CodeGen/GlobalISel/CombinerHelper.cpp | 16 +++++----- llvm/test/CodeGen/AArch64/fdiv-combine.ll | 31 +++++++++++++++++++ 2 files changed, 39 insertions(+), 8 deletions(-) diff --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp index a50641f219fbc..7a2124d48c9ac 100644 --- a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp +++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp @@ -6391,7 +6391,7 @@ bool CombinerHelper::matchCombineFMinMaxNaN(MachineInstr &MI, // Combine multiple FDIVs with the same divisor into multiple FMULs by the // reciprocal. -// E.g., (a / D; b / D;) -> (recip = 1.0 / D; a * recip; b * recip) +// E.g., (a / Y; b / Y;) -> (recip = 1.0 / Y; a * recip; b * recip) bool CombinerHelper::matchRepeatedFPDivisor( MachineInstr &MI, SmallVector &MatchInfo) const { assert(MI.getOpcode() == TargetOpcode::G_FDIV); @@ -6413,19 +6413,18 @@ bool CombinerHelper::matchRepeatedFPDivisor( // Exit early if the target does not want this transform or if there can't // possibly be enough uses of the divisor to make the transform worthwhile. unsigned MinUses = getTargetLowering().combineRepeatedFPDivisors(); - if (!MinUses) return false; - // Find all FDIV users of the same divisor. Use a set because duplicates may - // be present in the user list. For the moment we limit all instructions to a - // single BB and use the first Instr in MatchInfo as the dominating position. + // Find all FDIV users of the same divisor. For the moment we limit all + // instructions to a single BB and use the first Instr in MatchInfo as the + // dominating position. MatchInfo.push_back(&MI); for (auto &U : MRI.use_nodbg_instructions(Y)) { if (&U == &MI || U.getParent() != MI.getParent()) continue; if (U.getOpcode() == TargetOpcode::G_FDIV && - U.getOperand(2).getReg() == Y) { + U.getOperand(2).getReg() == Y && U.getOperand(1).getReg() != Y) { // This division is eligible for optimization only if global unsafe math // is enabled or if this division allows reciprocal formation. if (UnsafeMath || U.getFlag(MachineInstr::MIFlag::FmArcp)) { @@ -6448,13 +6447,14 @@ void CombinerHelper::applyRepeatedFPDivisor( Builder.setInsertPt(*MatchInfo[0]->getParent(), MatchInfo[0]); LLT Ty = MRI.getType(MatchInfo[0]->getOperand(0).getReg()); auto Div = Builder.buildFDiv(Ty, Builder.buildFConstant(Ty, 1.0), - MatchInfo[0]->getOperand(2).getReg()); + MatchInfo[0]->getOperand(2).getReg(), + MatchInfo[0]->getFlags()); // Replace all found div's with fmul instructions. for (MachineInstr *MI : MatchInfo) { Builder.setInsertPt(*MI->getParent(), MI); Builder.buildFMul(MI->getOperand(0).getReg(), MI->getOperand(1).getReg(), - Div->getOperand(0).getReg()); + Div->getOperand(0).getReg(), MI->getFlags()); MI->eraseFromParent(); } } diff --git a/llvm/test/CodeGen/AArch64/fdiv-combine.ll b/llvm/test/CodeGen/AArch64/fdiv-combine.ll index e566e54a2964a..107bc96fae376 100644 --- a/llvm/test/CodeGen/AArch64/fdiv-combine.ll +++ b/llvm/test/CodeGen/AArch64/fdiv-combine.ll @@ -103,6 +103,36 @@ define void @two_fdiv_double(double %D, double %a, double %b) #0 { ret void } +define void @four_fdiv_multi_float(float %D, float %a, float %b, float %c) #0 { +; CHECK-SD-LABEL: four_fdiv_multi_float: +; CHECK-SD: // %bb.0: +; CHECK-SD-NEXT: fmov s4, #1.00000000 +; CHECK-SD-NEXT: fdiv s5, s4, s0 +; CHECK-SD-NEXT: fmul s4, s1, s5 +; CHECK-SD-NEXT: fmul s1, s2, s5 +; CHECK-SD-NEXT: fmul s2, s3, s5 +; CHECK-SD-NEXT: fmul s3, s0, s5 +; CHECK-SD-NEXT: fmov s0, s4 +; CHECK-SD-NEXT: b foo_4f +; +; CHECK-GI-LABEL: four_fdiv_multi_float: +; CHECK-GI: // %bb.0: +; CHECK-GI-NEXT: fmov s4, #1.00000000 +; CHECK-GI-NEXT: fdiv s5, s4, s0 +; CHECK-GI-NEXT: fdiv s4, s0, s0 +; CHECK-GI-NEXT: fmul s0, s1, s5 +; CHECK-GI-NEXT: fmul s1, s2, s5 +; CHECK-GI-NEXT: fmul s2, s3, s5 +; CHECK-GI-NEXT: fmov s3, s4 +; CHECK-GI-NEXT: b foo_4f + %div = fdiv float %a, %D + %div1 = fdiv float %b, %D + %div2 = fdiv float %c, %D + %div3 = fdiv float %D, %D + tail call void @foo_4f(float %div, float %div1, float %div2, float %div3) + ret void +} + define void @splat_three_fdiv_4xfloat(float %D, <4 x float> %a, <4 x float> %b, <4 x float> %c) #0 { ; CHECK-LABEL: splat_three_fdiv_4xfloat: ; CHECK: // %bb.0: @@ -215,6 +245,7 @@ entry: } declare void @foo_3f(float, float, float) +declare void @foo_4f(float, float, float, float) declare void @foo_3d(double, double, double) declare void @foo_3_4xf(<4 x float>, <4 x float>, <4 x float>) declare void @foo_3_2xd(<2 x double>, <2 x double>, <2 x double>)