craig.topper created this revision. craig.topper added reviewers: bsmith, sdesmalen, c-rhodes, joechrisellis. Herald added subscribers: jobnoorman, luke, VincentWu, vkmr, frasercrmck, luismarques, apazos, sameer.abuasal, s.egerton, Jim, benna, psnobl, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, rogfer01, edward-jones, zzheng, jrtc27, shiva0217, kito-cheng, niosHD, sabuasal, simoncook, johnrusso, rbar, asb, kristof.beyls, arichardson. Herald added a project: All. craig.topper requested review of this revision. Herald added subscribers: wangpc, alextsao1999, eopXD. Herald added a project: clang.
This improves the codegen for calling a function that returns a VLST type. Previously we stored to an alloca using the scalable type, but loaded it using the fixed vector type. The middle end is unable to optimize away that store/load pair. With this patch we now store using the fixed vector type which matches the load. I have not added predicate types because I haven't supported those on RISC-V yet so I haven't seen a problem yet. Repository: rG LLVM Github Monorepo https://reviews.llvm.org/D155222 Files: clang/lib/CodeGen/CGCall.cpp clang/test/CodeGen/attr-arm-sve-vector-bits-call.c clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c Index: clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c =================================================================== --- clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c +++ clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c @@ -38,11 +38,7 @@ // CHECK-LABEL: @sizeless_caller( // CHECK-NEXT: entry: -// CHECK-NEXT: [[COERCE1:%.*]] = alloca <8 x i32>, align 8 -// CHECK-NEXT: store <vscale x 2 x i32> [[X:%.*]], ptr [[COERCE1]], align 8 -// CHECK-NEXT: [[TMP0:%.*]] = load <8 x i32>, ptr [[COERCE1]], align 8, !tbaa [[TBAA4:![0-9]+]] -// CHECK-NEXT: [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP0]], i64 0) -// CHECK-NEXT: ret <vscale x 2 x i32> [[CASTSCALABLESVE2]] +// CHECK-NEXT: ret <vscale x 2 x i32> [[X:%.*]] // vint32m1_t sizeless_caller(vint32m1_t x) { return fixed_callee(x); Index: clang/test/CodeGen/attr-arm-sve-vector-bits-call.c =================================================================== --- clang/test/CodeGen/attr-arm-sve-vector-bits-call.c +++ clang/test/CodeGen/attr-arm-sve-vector-bits-call.c @@ -41,11 +41,7 @@ // CHECK-LABEL: @sizeless_caller( // CHECK-NEXT: entry: -// CHECK-NEXT: [[COERCE1:%.*]] = alloca <16 x i32>, align 16 -// CHECK-NEXT: store <vscale x 4 x i32> [[X:%.*]], ptr [[COERCE1]], align 16 -// CHECK-NEXT: [[TMP1:%.*]] = load <16 x i32>, ptr [[COERCE1]], align 16, !tbaa [[TBAA6:![0-9]+]] -// CHECK-NEXT: [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TMP1]], i64 0) -// CHECK-NEXT: ret <vscale x 4 x i32> [[CASTSCALABLESVE2]] +// CHECK-NEXT: ret <vscale x 4 x i32> [[X:%.*]] // svint32_t sizeless_caller(svint32_t x) { return fixed_callee(x); Index: clang/lib/CodeGen/CGCall.cpp =================================================================== --- clang/lib/CodeGen/CGCall.cpp +++ clang/lib/CodeGen/CGCall.cpp @@ -1390,6 +1390,19 @@ return; } + // If coercing a fixed vector from a scalable vector for ABI compatibility, + // and the types match, use the llvm.vector.extract intrinsic to perform the + // conversion. + if (auto *FixedDst = dyn_cast<llvm::FixedVectorType>(DstTy)) { + if (auto *ScalableSrc = dyn_cast<llvm::ScalableVectorType>(SrcTy)) { + if (FixedDst->getElementType() == ScalableSrc->getElementType()) { + auto *Zero = llvm::Constant::getNullValue(CGF.CGM.Int64Ty); + Src = CGF.Builder.CreateExtractVector(DstTy, Src, Zero, "cast.fixed"); + CGF.Builder.CreateStore(Src, Dst, DstIsVolatile); + return; + } + } + } llvm::TypeSize DstSize = CGF.CGM.getDataLayout().getTypeAllocSize(DstTy); // If store is legal, just bitcast the src pointer.
Index: clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c =================================================================== --- clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c +++ clang/test/CodeGen/attr-riscv-rvv-vector-bits-call.c @@ -38,11 +38,7 @@ // CHECK-LABEL: @sizeless_caller( // CHECK-NEXT: entry: -// CHECK-NEXT: [[COERCE1:%.*]] = alloca <8 x i32>, align 8 -// CHECK-NEXT: store <vscale x 2 x i32> [[X:%.*]], ptr [[COERCE1]], align 8 -// CHECK-NEXT: [[TMP0:%.*]] = load <8 x i32>, ptr [[COERCE1]], align 8, !tbaa [[TBAA4:![0-9]+]] -// CHECK-NEXT: [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 2 x i32> @llvm.vector.insert.nxv2i32.v8i32(<vscale x 2 x i32> undef, <8 x i32> [[TMP0]], i64 0) -// CHECK-NEXT: ret <vscale x 2 x i32> [[CASTSCALABLESVE2]] +// CHECK-NEXT: ret <vscale x 2 x i32> [[X:%.*]] // vint32m1_t sizeless_caller(vint32m1_t x) { return fixed_callee(x); Index: clang/test/CodeGen/attr-arm-sve-vector-bits-call.c =================================================================== --- clang/test/CodeGen/attr-arm-sve-vector-bits-call.c +++ clang/test/CodeGen/attr-arm-sve-vector-bits-call.c @@ -41,11 +41,7 @@ // CHECK-LABEL: @sizeless_caller( // CHECK-NEXT: entry: -// CHECK-NEXT: [[COERCE1:%.*]] = alloca <16 x i32>, align 16 -// CHECK-NEXT: store <vscale x 4 x i32> [[X:%.*]], ptr [[COERCE1]], align 16 -// CHECK-NEXT: [[TMP1:%.*]] = load <16 x i32>, ptr [[COERCE1]], align 16, !tbaa [[TBAA6:![0-9]+]] -// CHECK-NEXT: [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TMP1]], i64 0) -// CHECK-NEXT: ret <vscale x 4 x i32> [[CASTSCALABLESVE2]] +// CHECK-NEXT: ret <vscale x 4 x i32> [[X:%.*]] // svint32_t sizeless_caller(svint32_t x) { return fixed_callee(x); Index: clang/lib/CodeGen/CGCall.cpp =================================================================== --- clang/lib/CodeGen/CGCall.cpp +++ clang/lib/CodeGen/CGCall.cpp @@ -1390,6 +1390,19 @@ return; } + // If coercing a fixed vector from a scalable vector for ABI compatibility, + // and the types match, use the llvm.vector.extract intrinsic to perform the + // conversion. + if (auto *FixedDst = dyn_cast<llvm::FixedVectorType>(DstTy)) { + if (auto *ScalableSrc = dyn_cast<llvm::ScalableVectorType>(SrcTy)) { + if (FixedDst->getElementType() == ScalableSrc->getElementType()) { + auto *Zero = llvm::Constant::getNullValue(CGF.CGM.Int64Ty); + Src = CGF.Builder.CreateExtractVector(DstTy, Src, Zero, "cast.fixed"); + CGF.Builder.CreateStore(Src, Dst, DstIsVolatile); + return; + } + } + } llvm::TypeSize DstSize = CGF.CGM.getDataLayout().getTypeAllocSize(DstTy); // If store is legal, just bitcast the src pointer.
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits