diff --git a/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp b/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp --- a/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp @@ -2289,6 +2289,25 @@ unsigned VWidth = cast(SVI.getType())->getNumElements(); unsigned LHSWidth = cast(LHS->getType())->getNumElements(); + + // shuffle (bitcast X), (bitcast Y), Mask --> bitcast (shuffle X, Y, Mask) + // + // if X and Y are of the same (vector) type, and the element size is not + // changed by the bitcasts, we can distribute the bitcasts through the + // shuffle, hopefully reducing the number of instructions. We make sure that + // at least one bitcast only has one use, so we don't *increase* the number of + // instructions here. + Value *X, *Y; + if (match(LHS, m_BitCast(m_Value(X))) && match(RHS, m_BitCast(m_Value(Y))) && + X->getType()->isVectorTy() && X->getType() == Y->getType() && + X->getType()->getScalarSizeInBits() == + SVI.getType()->getScalarSizeInBits() && + (LHS->hasOneUse() || RHS->hasOneUse())) { + Value *V = Builder.CreateShuffleVector(X, Y, SVI.getShuffleMask(), + SVI.getName() + ".uncasted"); + return new BitCastInst(V, SVI.getType()); + } + ArrayRef Mask = SVI.getShuffleMask(); Type *Int32Ty = Type::getInt32Ty(SVI.getContext()); @@ -2298,7 +2317,6 @@ // TODO: This could be extended to allow length-changing shuffles. // The transform might also be obsoleted if we allowed canonicalization // of bitcasted shuffles. - Value *X; if (match(LHS, m_BitCast(m_Value(X))) && match(RHS, m_Undef()) && X->getType()->isVectorTy() && VWidth == LHSWidth) { // Try to create a scaled mask constant. diff --git a/llvm/test/Transforms/InstCombine/shuffle-cast-dist.ll b/llvm/test/Transforms/InstCombine/shuffle-cast-dist.ll --- a/llvm/test/Transforms/InstCombine/shuffle-cast-dist.ll +++ b/llvm/test/Transforms/InstCombine/shuffle-cast-dist.ll @@ -4,9 +4,8 @@ define <2 x float> @vtrn1(<2 x i32> %v) ; CHECK-LABEL: @vtrn1( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[VB1:%.*]] = bitcast <2 x i32> [[V:%.*]] to <2 x float> -; CHECK-NEXT: [[VB2:%.*]] = bitcast <2 x i32> [[V]] to <2 x float> -; CHECK-NEXT: [[R:%.*]] = shufflevector <2 x float> [[VB1]], <2 x float> [[VB2]], <2 x i32> +; CHECK-NEXT: [[R_UNCASTED:%.*]] = shufflevector <2 x i32> [[V:%.*]], <2 x i32> undef, <2 x i32> zeroinitializer +; CHECK-NEXT: [[R:%.*]] = bitcast <2 x i32> [[R_UNCASTED]] to <2 x float> ; CHECK-NEXT: ret <2 x float> [[R]] ; { @@ -20,9 +19,8 @@ define <2 x float> @vtrn2(<2 x i32> %x, <2 x i32> %y) { ; CHECK-LABEL: @vtrn2( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[XB:%.*]] = bitcast <2 x i32> [[X:%.*]] to <2 x float> -; CHECK-NEXT: [[YB:%.*]] = bitcast <2 x i32> [[Y:%.*]] to <2 x float> -; CHECK-NEXT: [[R:%.*]] = shufflevector <2 x float> [[XB]], <2 x float> [[YB]], <2 x i32> +; CHECK-NEXT: [[R_UNCASTED:%.*]] = shufflevector <2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <2 x i32> +; CHECK-NEXT: [[R:%.*]] = bitcast <2 x i32> [[R_UNCASTED]] to <2 x float> ; CHECK-NEXT: ret <2 x float> [[R]] ; entry: @@ -35,9 +33,8 @@ define <4 x float> @bc_shuf_lenchange(<2 x i32> %x, <2 x i32> %y) { ; CHECK-LABEL: @bc_shuf_lenchange( -; CHECK-NEXT: [[XB:%.*]] = bitcast <2 x i32> [[X:%.*]] to <2 x float> -; CHECK-NEXT: [[YB:%.*]] = bitcast <2 x i32> [[Y:%.*]] to <2 x float> -; CHECK-NEXT: [[R:%.*]] = shufflevector <2 x float> [[XB]], <2 x float> [[YB]], <4 x i32> +; CHECK-NEXT: [[R_UNCASTED:%.*]] = shufflevector <2 x i32> [[X:%.*]], <2 x i32> [[Y:%.*]], <4 x i32> +; CHECK-NEXT: [[R:%.*]] = bitcast <4 x i32> [[R_UNCASTED]] to <4 x float> ; CHECK-NEXT: ret <4 x float> [[R]] ; %xb = bitcast <2 x i32> %x to <2 x float> @@ -126,9 +123,9 @@ define <4 x float> @bc_shuf_y_hasoneuse(<4 x i32> %x, <4 x i32> %y){ ; CHECK-LABEL: @bc_shuf_y_hasoneuse( ; CHECK-NEXT: [[XB:%.*]] = bitcast <4 x i32> [[X:%.*]] to <4 x float> -; CHECK-NEXT: [[YB:%.*]] = bitcast <4 x i32> [[Y:%.*]] to <4 x float> -; CHECK-NEXT: [[SHUF:%.*]] = shufflevector <4 x float> [[XB]], <4 x float> [[YB]], <4 x i32> -; CHECK-NEXT: [[R:%.*]] = fadd <4 x float> [[SHUF]], [[XB]] +; CHECK-NEXT: [[SHUF_UNCASTED:%.*]] = shufflevector <4 x i32> [[X]], <4 x i32> [[Y:%.*]], <4 x i32> +; CHECK-NEXT: [[SHUF:%.*]] = bitcast <4 x i32> [[SHUF_UNCASTED]] to <4 x float> +; CHECK-NEXT: [[R:%.*]] = fadd <4 x float> [[XB]], [[SHUF]] ; CHECK-NEXT: ret <4 x float> [[R]] ; %xb = bitcast <4 x i32> %x to <4 x float>