diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp --- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp +++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp @@ -1574,6 +1574,30 @@ } break; } + case Intrinsic::smin: + case Intrinsic::smax: + case Intrinsic::umin: + case Intrinsic::umax: { + if (!ST->hasMVEIntegerOps()) + break; + Type *VT = ICA.getReturnType(); + + std::pair LT = TLI->getTypeLegalizationCost(DL, VT); + if (LT.second == MVT::v4i32 || LT.second == MVT::v8i16 || + LT.second == MVT::v16i8) + return LT.first * ST->getMVEVectorCostFactor(CostKind); + break; + } + case Intrinsic::minnum: + case Intrinsic::maxnum: { + if (!ST->hasMVEFloatOps()) + break; + Type *VT = ICA.getReturnType(); + std::pair LT = TLI->getTypeLegalizationCost(DL, VT); + if (LT.second == MVT::v4f32 || LT.second == MVT::v8f16) + return LT.first * ST->getMVEVectorCostFactor(CostKind); + break; + } } return BaseT::getIntrinsicInstrCost(ICA, CostKind); diff --git a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll --- a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll +++ b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll @@ -43,7 +43,7 @@ define void @smax(i32 %a, i32 %b, <16 x i32> %va, <16 x i32> %vb) { ; THRU-LABEL: 'smax' ; THRU-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %s = call i32 @llvm.smax.i32(i32 %a, i32 %b) -; THRU-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb) +; THRU-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb) ; THRU-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; LATE-LABEL: 'smax' @@ -53,12 +53,12 @@ ; ; SIZE-LABEL: 'smax' ; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %s = call i32 @llvm.smax.i32(i32 %a, i32 %b) -; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb) +; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb) ; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void ; ; SIZE_LATE-LABEL: 'smax' ; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %s = call i32 @llvm.smax.i32(i32 %a, i32 %b) -; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb) +; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v = call <16 x i32> @llvm.smax.v16i32(<16 x i32> %va, <16 x i32> %vb) ; SIZE_LATE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void ; %s = call i32 @llvm.smax.i32(i32 %a, i32 %b) diff --git a/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll b/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll --- a/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll +++ b/llvm/test/Analysis/CostModel/ARM/mve-minmax.ll @@ -38,22 +38,22 @@ ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; MVE-SIZE-LABEL: 'smin' @@ -63,22 +63,22 @@ ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef) @@ -145,22 +145,22 @@ ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; MVE-SIZE-LABEL: 'smax' @@ -170,22 +170,22 @@ ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef) @@ -253,22 +253,22 @@ ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; MVE-SIZE-LABEL: 'umin' @@ -278,22 +278,22 @@ ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef) @@ -360,22 +360,22 @@ ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 304 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef) +; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef ; ; MVE-SIZE-LABEL: 'sub' @@ -385,22 +385,22 @@ ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef) -; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef) +; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef) ; MVE-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef ; %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef) @@ -495,14 +495,14 @@ ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef @@ -515,14 +515,14 @@ ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.minnum.f32(float undef, float undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.minnum.f16(half undef, half undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32F16 = call <32 x half> @llvm.minnum.v32f16(<32 x half> undef, <32 x half> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef ; %F64 = call double @llvm.minnum.f64(double undef, double undef) @@ -607,14 +607,14 @@ ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V4F64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 144 for instruction: %V8F64 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef) -; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef) +; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef) ; MVEF-RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float undef @@ -627,14 +627,14 @@ ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.maxnum.f32(float undef, float undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F16 = call half @llvm.maxnum.f16(half undef, half undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef) -; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef) +; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32F16 = call <32 x half> @llvm.maxnum.v32f16(<32 x half> undef, <32 x half> undef) ; MVEF-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret float undef ; %F64 = call double @llvm.maxnum.f64(double undef, double undef)