llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-amdgpu Author: Matt Arsenault (arsenm) <details> <summary>Changes</summary> --- Patch is 245.20 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/100518.diff 8 Files Affected: - (modified) llvm/include/llvm/CodeGen/BasicTTIImpl.h (+52-38) - (modified) llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll (+12-12) - (modified) llvm/test/Analysis/CostModel/ARM/arith-overflow.ll (+152-152) - (modified) llvm/test/Analysis/CostModel/ARM/arith-ssat.ll (+86-86) - (modified) llvm/test/Analysis/CostModel/ARM/arith-usat.ll (+84-84) - (modified) llvm/test/Analysis/CostModel/X86/arith-ssat-codesize.ll (+44-44) - (modified) llvm/test/Analysis/CostModel/X86/arith-ssat-latency.ll (+44-44) - (modified) llvm/test/Analysis/CostModel/X86/arith-ssat-sizelatency.ll (+44-44) ``````````diff diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h index c842e4a2c4320..a89d4fe467eb9 100644 --- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h +++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h @@ -2180,44 +2180,17 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> { return Cost; } case Intrinsic::sadd_with_overflow: - case Intrinsic::ssub_with_overflow: { - Type *SumTy = RetTy->getContainedType(0); - Type *OverflowTy = RetTy->getContainedType(1); - unsigned Opcode = IID == Intrinsic::sadd_with_overflow - ? BinaryOperator::Add - : BinaryOperator::Sub; - - // Add: - // Overflow -> (Result < LHS) ^ (RHS < 0) - // Sub: - // Overflow -> (Result < LHS) ^ (RHS > 0) - InstructionCost Cost = 0; - Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind); - Cost += 2 * thisT()->getCmpSelInstrCost( - Instruction::ICmp, SumTy, OverflowTy, - CmpInst::ICMP_SGT, CostKind); - Cost += thisT()->getArithmeticInstrCost(BinaryOperator::Xor, OverflowTy, - CostKind); - return Cost; - } + ISD = ISD::SADDO; + break; + case Intrinsic::ssub_with_overflow: + ISD = ISD::SSUBO; + break; case Intrinsic::uadd_with_overflow: - case Intrinsic::usub_with_overflow: { - Type *SumTy = RetTy->getContainedType(0); - Type *OverflowTy = RetTy->getContainedType(1); - unsigned Opcode = IID == Intrinsic::uadd_with_overflow - ? BinaryOperator::Add - : BinaryOperator::Sub; - CmpInst::Predicate Pred = IID == Intrinsic::uadd_with_overflow - ? CmpInst::ICMP_ULT - : CmpInst::ICMP_UGT; - - InstructionCost Cost = 0; - Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind); - Cost += - thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy, OverflowTy, - Pred, CostKind); - return Cost; - } + ISD = ISD::UADDO; + break; + case Intrinsic::usub_with_overflow: + ISD = ISD::USUBO; + break; case Intrinsic::smul_with_overflow: case Intrinsic::umul_with_overflow: { Type *MulTy = RetTy->getContainedType(0); @@ -2296,8 +2269,11 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> { break; } + auto *ST = dyn_cast<StructType>(RetTy); + Type *LegalizeTy = ST ? ST->getContainedType(0) : RetTy; + std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(LegalizeTy); + const TargetLoweringBase *TLI = getTLI(); - std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(RetTy); if (TLI->isOperationLegalOrPromote(ISD, LT.second)) { if (IID == Intrinsic::fabs && LT.second.isFloatingPoint() && @@ -2353,6 +2329,44 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> { Pred, CostKind); return Cost; } + case Intrinsic::sadd_with_overflow: + case Intrinsic::ssub_with_overflow: { + Type *SumTy = RetTy->getContainedType(0); + Type *OverflowTy = RetTy->getContainedType(1); + unsigned Opcode = IID == Intrinsic::sadd_with_overflow + ? BinaryOperator::Add + : BinaryOperator::Sub; + + // Add: + // Overflow -> (Result < LHS) ^ (RHS < 0) + // Sub: + // Overflow -> (Result < LHS) ^ (RHS > 0) + InstructionCost Cost = 0; + Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind); + Cost += + 2 * thisT()->getCmpSelInstrCost(Instruction::ICmp, SumTy, OverflowTy, + CmpInst::ICMP_SGT, CostKind); + Cost += thisT()->getArithmeticInstrCost(BinaryOperator::Xor, OverflowTy, + CostKind); + return Cost; + } + case Intrinsic::uadd_with_overflow: + case Intrinsic::usub_with_overflow: { + Type *SumTy = RetTy->getContainedType(0); + Type *OverflowTy = RetTy->getContainedType(1); + unsigned Opcode = IID == Intrinsic::uadd_with_overflow + ? BinaryOperator::Add + : BinaryOperator::Sub; + CmpInst::Predicate Pred = IID == Intrinsic::uadd_with_overflow + ? CmpInst::ICMP_ULT + : CmpInst::ICMP_UGT; + + InstructionCost Cost = 0; + Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind); + Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy, + OverflowTy, Pred, CostKind); + return Cost; + } case Intrinsic::sadd_sat: case Intrinsic::ssub_sat: { // Assume a default expansion. diff --git a/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll b/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll index cdd61c147fdad..c6f1cbab80438 100644 --- a/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll +++ b/llvm/test/Analysis/CostModel/ARM/active_lane_mask.ll @@ -3,18 +3,18 @@ define void @get_lane_mask() { ; CHECK-LABEL: 'get_lane_mask' -; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %mask_v8i1_i16 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i16(i16 undef, i16 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %mask_v4i1_i16 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i16(i16 undef, i16 undef) -; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %mask_v2i1_i16 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i16(i16 undef, i16 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %mask_v8i1_i16 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i16(i16 undef, i16 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %mask_v4i1_i16 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i16(i16 undef, i16 undef) +; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %mask_v2i1_i16 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i16(i16 undef, i16 undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void ; %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef) diff --git a/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll b/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll index 67ab70569175e..484cd201d14a0 100644 --- a/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll +++ b/llvm/test/Analysis/CostModel/ARM/arith-overflow.ll @@ -30,79 +30,79 @@ declare {<64 x i8>, <64 x i1>} @llvm.sadd.with.overflow.v64i8(<64 x i8>, <64 x define i32 @sadd(i32 %arg) { ; V8M-RECIP-LABEL: 'sadd' -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) -; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 384 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) +; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef) ; V8M-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; ; NEON-RECIP-LABEL: 'sadd' -; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef) +; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef) -; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef) +; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef) -; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef) +; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef) -; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef) +; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef) ; NEON-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; MVE-RECIP-LABEL: 'sadd' -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 218 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 434 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef) ; MVE-RECIP-NEXT: Cost Model... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/100518 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
