Index: lib/Analysis/InstructionSimplify.cpp =================================================================== --- lib/Analysis/InstructionSimplify.cpp +++ lib/Analysis/InstructionSimplify.cpp @@ -2488,6 +2488,20 @@ static Value *simplifyICmpWithConstant(CmpInst::Predicate Pred, Value *LHS, Value *RHS) { + Type *ITy = GetCompareTy(RHS); // The return type. + + Value *X; + // Sign-bit checks can be optimized to true/false after unsigned + // floating-point casts: + // icmp slt (bitcast (uitofp X)), 0 --> false + // icmp sgt (bitcast (uitofp X)), -1 --> true + if (match(LHS, m_BitCast(m_UIToFP(m_Value(X))))) { + if (Pred == ICmpInst::ICMP_SLT && match(RHS, m_Zero())) + return ConstantInt::getFalse(ITy); + if (Pred == ICmpInst::ICMP_SGT && match(RHS, m_AllOnes())) + return ConstantInt::getTrue(ITy); + } + const APInt *C; if (!match(RHS, m_APInt(C))) return nullptr; @@ -2495,9 +2509,9 @@ // Rule out tautological comparisons (eg., ult 0 or uge 0). ConstantRange RHS_CR = ConstantRange::makeExactICmpRegion(Pred, *C); if (RHS_CR.isEmptySet()) - return ConstantInt::getFalse(GetCompareTy(RHS)); + return ConstantInt::getFalse(ITy); if (RHS_CR.isFullSet()) - return ConstantInt::getTrue(GetCompareTy(RHS)); + return ConstantInt::getTrue(ITy); // Find the range of possible values for binary operators. unsigned Width = C->getBitWidth(); @@ -2515,9 +2529,9 @@ if (!LHS_CR.isFullSet()) { if (RHS_CR.contains(LHS_CR)) - return ConstantInt::getTrue(GetCompareTy(RHS)); + return ConstantInt::getTrue(ITy); if (RHS_CR.inverse().contains(LHS_CR)) - return ConstantInt::getFalse(GetCompareTy(RHS)); + return ConstantInt::getFalse(ITy); } return nullptr; Index: test/Transforms/InstSimplify/cast-unsigned-icmp-cmp-0.ll =================================================================== --- test/Transforms/InstSimplify/cast-unsigned-icmp-cmp-0.ll +++ test/Transforms/InstSimplify/cast-unsigned-icmp-cmp-0.ll @@ -1,20 +1,17 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt < %s -instsimplify -S | FileCheck %s -; target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" - ; This is related to https://bugs.llvm.org/show_bug.cgi?id=36682 -; FIXME: All of these can be simplified to a constant true or false value. +; All of these can be simplified to a constant true or false value. ; * slt i32 %b, 0 -> false ; * sgt i32 %b, -1 -> true +; FIXME: m_Zero does not handle undef elements in vectors. + define i1 @i32_cast_cmp_slt_int_0_uitofp_float(i32 %i) { ; CHECK-LABEL: @i32_cast_cmp_slt_int_0_uitofp_float( -; CHECK-NEXT: [[F:%.*]] = uitofp i32 [[I:%.*]] to float -; CHECK-NEXT: [[B:%.*]] = bitcast float [[F]] to i32 -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[B]], 0 -; CHECK-NEXT: ret i1 [[CMP]] +; CHECK-NEXT: ret i1 false ; %f = uitofp i32 %i to float %b = bitcast float %f to i32 @@ -24,10 +21,7 @@ define <2 x i1> @i32_cast_cmp_slt_int_0_uitofp_float_vec(<2 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_slt_int_0_uitofp_float_vec( -; CHECK-NEXT: [[F:%.*]] = uitofp <2 x i32> [[I:%.*]] to <2 x float> -; CHECK-NEXT: [[B:%.*]] = bitcast <2 x float> [[F]] to <2 x i32> -; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i32> [[B]], zeroinitializer -; CHECK-NEXT: ret <2 x i1> [[CMP]] +; CHECK-NEXT: ret <2 x i1> zeroinitializer ; %f = uitofp <2 x i32> %i to <2 x float> %b = bitcast <2 x float> %f to <2 x i32> @@ -50,10 +44,7 @@ define i1 @i32_cast_cmp_sgt_int_m1_uitofp_float(i32 %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_float( -; CHECK-NEXT: [[F:%.*]] = uitofp i32 [[I:%.*]] to float -; CHECK-NEXT: [[B:%.*]] = bitcast float [[F]] to i32 -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i32 [[B]], -1 -; CHECK-NEXT: ret i1 [[CMP]] +; CHECK-NEXT: ret i1 true ; %f = uitofp i32 %i to float %b = bitcast float %f to i32 @@ -63,10 +54,7 @@ define <2 x i1> @i32_cast_cmp_sgt_int_m1_uitofp_float_vec(<2 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_float_vec( -; CHECK-NEXT: [[F:%.*]] = uitofp <2 x i32> [[I:%.*]] to <2 x float> -; CHECK-NEXT: [[B:%.*]] = bitcast <2 x float> [[F]] to <2 x i32> -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i32> [[B]], -; CHECK-NEXT: ret <2 x i1> [[CMP]] +; CHECK-NEXT: ret <2 x i1> ; %f = uitofp <2 x i32> %i to <2 x float> %b = bitcast <2 x float> %f to <2 x i32> @@ -76,10 +64,7 @@ define <3 x i1> @i32_cast_cmp_sgt_int_m1_uitofp_float_vec_undef(<3 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_float_vec_undef( -; CHECK-NEXT: [[F:%.*]] = uitofp <3 x i32> [[I:%.*]] to <3 x float> -; CHECK-NEXT: [[B:%.*]] = bitcast <3 x float> [[F]] to <3 x i32> -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <3 x i32> [[B]], -; CHECK-NEXT: ret <3 x i1> [[CMP]] +; CHECK-NEXT: ret <3 x i1> ; %f = uitofp <3 x i32> %i to <3 x float> %b = bitcast <3 x float> %f to <3 x i32> @@ -89,10 +74,7 @@ define i1 @i32_cast_cmp_slt_int_0_uitofp_double(i32 %i) { ; CHECK-LABEL: @i32_cast_cmp_slt_int_0_uitofp_double( -; CHECK-NEXT: [[F:%.*]] = uitofp i32 [[I:%.*]] to double -; CHECK-NEXT: [[B:%.*]] = bitcast double [[F]] to i64 -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i64 [[B]], 0 -; CHECK-NEXT: ret i1 [[CMP]] +; CHECK-NEXT: ret i1 false ; %f = uitofp i32 %i to double %b = bitcast double %f to i64 @@ -102,10 +84,7 @@ define <2 x i1> @i32_cast_cmp_slt_int_0_uitofp_double_vec(<2 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_slt_int_0_uitofp_double_vec( -; CHECK-NEXT: [[F:%.*]] = uitofp <2 x i32> [[I:%.*]] to <2 x double> -; CHECK-NEXT: [[B:%.*]] = bitcast <2 x double> [[F]] to <2 x i64> -; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i64> [[B]], zeroinitializer -; CHECK-NEXT: ret <2 x i1> [[CMP]] +; CHECK-NEXT: ret <2 x i1> zeroinitializer ; %f = uitofp <2 x i32> %i to <2 x double> %b = bitcast <2 x double> %f to <2 x i64> @@ -128,10 +107,7 @@ define i1 @i32_cast_cmp_sgt_int_m1_uitofp_double(i32 %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_double( -; CHECK-NEXT: [[F:%.*]] = uitofp i32 [[I:%.*]] to double -; CHECK-NEXT: [[B:%.*]] = bitcast double [[F]] to i64 -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i64 [[B]], -1 -; CHECK-NEXT: ret i1 [[CMP]] +; CHECK-NEXT: ret i1 true ; %f = uitofp i32 %i to double %b = bitcast double %f to i64 @@ -141,10 +117,7 @@ define <2 x i1> @i32_cast_cmp_sgt_int_m1_uitofp_double_vec(<2 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_double_vec( -; CHECK-NEXT: [[F:%.*]] = uitofp <2 x i32> [[I:%.*]] to <2 x double> -; CHECK-NEXT: [[B:%.*]] = bitcast <2 x double> [[F]] to <2 x i64> -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i64> [[B]], -; CHECK-NEXT: ret <2 x i1> [[CMP]] +; CHECK-NEXT: ret <2 x i1> ; %f = uitofp <2 x i32> %i to <2 x double> %b = bitcast <2 x double> %f to <2 x i64> @@ -154,10 +127,7 @@ define <3 x i1> @i32_cast_cmp_sgt_int_m1_uitofp_double_vec_undef(<3 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_double_vec_undef( -; CHECK-NEXT: [[F:%.*]] = uitofp <3 x i32> [[I:%.*]] to <3 x double> -; CHECK-NEXT: [[B:%.*]] = bitcast <3 x double> [[F]] to <3 x i64> -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <3 x i64> [[B]], -; CHECK-NEXT: ret <3 x i1> [[CMP]] +; CHECK-NEXT: ret <3 x i1> ; %f = uitofp <3 x i32> %i to <3 x double> %b = bitcast <3 x double> %f to <3 x i64> @@ -167,10 +137,7 @@ define i1 @i32_cast_cmp_slt_int_0_uitofp_half(i32 %i) { ; CHECK-LABEL: @i32_cast_cmp_slt_int_0_uitofp_half( -; CHECK-NEXT: [[F:%.*]] = uitofp i32 [[I:%.*]] to half -; CHECK-NEXT: [[B:%.*]] = bitcast half [[F]] to i16 -; CHECK-NEXT: [[CMP:%.*]] = icmp slt i16 [[B]], 0 -; CHECK-NEXT: ret i1 [[CMP]] +; CHECK-NEXT: ret i1 false ; %f = uitofp i32 %i to half %b = bitcast half %f to i16 @@ -180,10 +147,7 @@ define <2 x i1> @i32_cast_cmp_slt_int_0_uitofp_half_vec(<2 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_slt_int_0_uitofp_half_vec( -; CHECK-NEXT: [[F:%.*]] = uitofp <2 x i32> [[I:%.*]] to <2 x half> -; CHECK-NEXT: [[B:%.*]] = bitcast <2 x half> [[F]] to <2 x i16> -; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i16> [[B]], zeroinitializer -; CHECK-NEXT: ret <2 x i1> [[CMP]] +; CHECK-NEXT: ret <2 x i1> zeroinitializer ; %f = uitofp <2 x i32> %i to <2 x half> %b = bitcast <2 x half> %f to <2 x i16> @@ -206,10 +170,7 @@ define i1 @i32_cast_cmp_sgt_int_m1_uitofp_half(i32 %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_half( -; CHECK-NEXT: [[F:%.*]] = uitofp i32 [[I:%.*]] to half -; CHECK-NEXT: [[B:%.*]] = bitcast half [[F]] to i16 -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i16 [[B]], -1 -; CHECK-NEXT: ret i1 [[CMP]] +; CHECK-NEXT: ret i1 true ; %f = uitofp i32 %i to half %b = bitcast half %f to i16 @@ -219,10 +180,7 @@ define <2 x i1> @i32_cast_cmp_sgt_int_m1_uitofp_half_vec(<2 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_half_vec( -; CHECK-NEXT: [[F:%.*]] = uitofp <2 x i32> [[I:%.*]] to <2 x half> -; CHECK-NEXT: [[B:%.*]] = bitcast <2 x half> [[F]] to <2 x i16> -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i16> [[B]], -; CHECK-NEXT: ret <2 x i1> [[CMP]] +; CHECK-NEXT: ret <2 x i1> ; %f = uitofp <2 x i32> %i to <2 x half> %b = bitcast <2 x half> %f to <2 x i16> @@ -232,10 +190,7 @@ define <3 x i1> @i32_cast_cmp_sgt_int_m1_uitofp_half_vec_undef(<3 x i32> %i) { ; CHECK-LABEL: @i32_cast_cmp_sgt_int_m1_uitofp_half_vec_undef( -; CHECK-NEXT: [[F:%.*]] = uitofp <3 x i32> [[I:%.*]] to <3 x half> -; CHECK-NEXT: [[B:%.*]] = bitcast <3 x half> [[F]] to <3 x i16> -; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <3 x i16> [[B]], -; CHECK-NEXT: ret <3 x i1> [[CMP]] +; CHECK-NEXT: ret <3 x i1> ; %f = uitofp <3 x i32> %i to <3 x half> %b = bitcast <3 x half> %f to <3 x i16>