llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clangir Author: AIT (GeneraluseAI) <details> <summary>Changes</summary> Part of [#<!-- -->167765 ](https://github.com/llvm/llvm-project/issues/167765) (kadd, kand, kandn, kor, kxor, knot, kmov) adds CIR codegen support for AVX512 mask operations on X86, including kadd, kand, kandn, kor, kxor, knot, and kmov in all supported mask widths. also adds comprehensive CIR/LLVM/OGCG tests for AVX512F, AVX512DQ, and AVX512BW to validate the lowering behavior. --- Patch is 35.08 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/169185.diff 4 Files Affected: - (modified) clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp (+90-3) - (added) clang/test/CIR/CodeGen/X86/avx512bw-builtins.c (+308) - (added) clang/test/CIR/CodeGen/X86/avx512dq-builtins.c (+213) - (added) clang/test/CIR/CodeGen/X86/avx512f-builtins.c (+143) ``````````diff diff --git a/clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp b/clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp index a30c79a83751a..1a19fd204f42c 100644 --- a/clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp +++ b/clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp @@ -68,6 +68,45 @@ static mlir::Value emitVectorFCmp(CIRGenBuilderTy &builder, return bitCast; } +// Convert the mask from an integer type to a vector of i1. +static mlir::Value getMaskVecValue(CIRGenFunction &cgf, const CallExpr *expr, + mlir::Value mask, unsigned numElems) { + auto &builder = cgf.getBuilder(); + + cir::VectorType maskTy = + cir::VectorType::get(cgf.getBuilder().getSIntNTy(1), + cast<cir::IntType>(mask.getType()).getWidth()); + mlir::Value maskVec = builder.createBitcast(mask, maskTy); + + // If we have less than 8 elements, then the starting mask was an i8 and + // we need to extract down to the right number of elements. + if (numElems < 8) { + SmallVector<mlir::Attribute, 4> indices; + mlir::Type i32Ty = builder.getI32Type(); + for (auto i : llvm::seq<unsigned>(0, numElems)) + indices.push_back(cir::IntAttr::get(i32Ty, i)); + maskVec = builder.createVecShuffle(cgf.getLoc(expr->getExprLoc()), maskVec, + maskVec, indices); + } + return maskVec; +} + +static mlir::Value emitX86MaskLogic(CIRGenFunction &cgf, const CallExpr *expr, + cir::BinOpKind opc, + SmallVectorImpl<mlir::Value> &ops, + bool InvertLHS = false) { + CIRGenBuilderTy &builder = cgf.getBuilder(); + unsigned numElts = cast<cir::IntType>(ops[0].getType()).getWidth(); + mlir::Value LHS = getMaskVecValue(cgf, expr, ops[0], numElts); + mlir::Value RHS = getMaskVecValue(cgf, expr, ops[1], numElts); + + if (InvertLHS) + LHS = builder.createNot(LHS); + return builder.createBitcast( + builder.createBinop(cgf.getLoc(expr->getExprLoc()), LHS, opc, RHS), + ops[0].getType()); +} + mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID, const CallExpr *expr) { if (builtinID == Builtin::BI__builtin_cpu_is) { @@ -672,38 +711,86 @@ mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID, case X86::BI__builtin_ia32_ktestzsi: case X86::BI__builtin_ia32_ktestcdi: case X86::BI__builtin_ia32_ktestzdi: + cgm.errorNYI(expr->getSourceRange(), + std::string("unimplemented X86 builtin call: ") + + getContext().BuiltinInfo.getName(builtinID)); + return {}; case X86::BI__builtin_ia32_kaddqi: case X86::BI__builtin_ia32_kaddhi: case X86::BI__builtin_ia32_kaddsi: - case X86::BI__builtin_ia32_kadddi: + case X86::BI__builtin_ia32_kadddi: { + std::string intrinsicName; + switch (builtinID) { + default: + llvm_unreachable("Unsupported intrinsic!"); + case X86::BI__builtin_ia32_kaddqi: + intrinsicName = "x86.avx512.kadd.b"; + break; + case X86::BI__builtin_ia32_kaddhi: + intrinsicName = "x86.avx512.kadd.w"; + break; + case X86::BI__builtin_ia32_kaddsi: + intrinsicName = "x86.avx512.kadd.d"; + break; + case X86::BI__builtin_ia32_kadddi: + intrinsicName = "x86.avx512.kadd.q"; + break; + } + auto intTy = cast<cir::IntType>(ops[0].getType()); + unsigned numElts = intTy.getWidth(); + mlir::Value lhsVec = getMaskVecValue(*this, expr, ops[0], numElts); + mlir::Value rhsVec = getMaskVecValue(*this, expr, ops[1], numElts); + mlir::Type vecTy = lhsVec.getType(); + mlir::Value resVec = emitIntrinsicCallOp(*this, expr, intrinsicName, vecTy, + mlir::ValueRange{lhsVec, rhsVec}); + return builder.createBitcast(resVec, ops[0].getType()); + } case X86::BI__builtin_ia32_kandqi: case X86::BI__builtin_ia32_kandhi: case X86::BI__builtin_ia32_kandsi: case X86::BI__builtin_ia32_kanddi: + return emitX86MaskLogic(*this, expr, cir::BinOpKind::And, ops); case X86::BI__builtin_ia32_kandnqi: case X86::BI__builtin_ia32_kandnhi: case X86::BI__builtin_ia32_kandnsi: case X86::BI__builtin_ia32_kandndi: + return emitX86MaskLogic(*this, expr, cir::BinOpKind::And, ops, true); case X86::BI__builtin_ia32_korqi: case X86::BI__builtin_ia32_korhi: case X86::BI__builtin_ia32_korsi: case X86::BI__builtin_ia32_kordi: + return emitX86MaskLogic(*this, expr, cir::BinOpKind::Or, ops); case X86::BI__builtin_ia32_kxnorqi: case X86::BI__builtin_ia32_kxnorhi: case X86::BI__builtin_ia32_kxnorsi: case X86::BI__builtin_ia32_kxnordi: + return emitX86MaskLogic(*this, expr, cir::BinOpKind::Xor, ops, true); case X86::BI__builtin_ia32_kxorqi: case X86::BI__builtin_ia32_kxorhi: case X86::BI__builtin_ia32_kxorsi: case X86::BI__builtin_ia32_kxordi: + return emitX86MaskLogic(*this, expr, cir::BinOpKind::Xor, ops); case X86::BI__builtin_ia32_knotqi: case X86::BI__builtin_ia32_knothi: case X86::BI__builtin_ia32_knotsi: - case X86::BI__builtin_ia32_knotdi: + case X86::BI__builtin_ia32_knotdi: { + cir::IntType intTy = cast<cir::IntType>(ops[0].getType()); + unsigned numElts = intTy.getWidth(); + mlir::Value resVec = getMaskVecValue(*this, expr, ops[0], numElts); + return builder.createBitcast(builder.createNot(resVec), ops[0].getType()); + } case X86::BI__builtin_ia32_kmovb: case X86::BI__builtin_ia32_kmovw: case X86::BI__builtin_ia32_kmovd: - case X86::BI__builtin_ia32_kmovq: + case X86::BI__builtin_ia32_kmovq: { + // Bitcast to vXi1 type and then back to integer. This gets the mask + // register type into the IR, but might be optimized out depending on + // what's around it. + cir::IntType intTy = cast<cir::IntType>(ops[0].getType()); + unsigned numElts = intTy.getWidth(); + mlir::Value resVec = getMaskVecValue(*this, expr, ops[0], numElts); + return builder.createBitcast(resVec, ops[0].getType()); + } case X86::BI__builtin_ia32_kunpckdi: case X86::BI__builtin_ia32_kunpcksi: case X86::BI__builtin_ia32_kunpckhi: diff --git a/clang/test/CIR/CodeGen/X86/avx512bw-builtins.c b/clang/test/CIR/CodeGen/X86/avx512bw-builtins.c new file mode 100644 index 0000000000000..0d5aa2918e922 --- /dev/null +++ b/clang/test/CIR/CodeGen/X86/avx512bw-builtins.c @@ -0,0 +1,308 @@ + // RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512bw -fclangir -emit-cir -o %t.cir -Wall -Werror + // RUN: FileCheck --check-prefix=CIR --input-file=%t.cir %s + // RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512bw -fclangir -emit-llvm -o %t.ll -Wall -Werror + // RUN: FileCheck --check-prefix=LLVM --input-file=%t.ll %s + + // RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512bw -fno-signed-char -fclangir -emit-cir -o %t.cir -Wall -Werror + // RUN: FileCheck --check-prefix=CIR --input-file=%t.cir %s + // RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512bw -fno-signed-char -fclangir -emit-llvm -o %t.ll -Wall -Werror + // RUN: FileCheck --check-prefix=LLVM --input-file=%t.ll %s + + // RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512bw -emit-llvm -o - -Wall -Werror | FileCheck %s -check-prefix=OGCG + // RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512bw -emit-llvm -o - -Wall -Werror | FileCheck %s -check-prefix=OGCG + + #include <immintrin.h> + +__mmask32 test_kadd_mask32(__mmask32 A, __mmask32 B) { + // CIR-LABEL: _kadd_mask32 + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.call_llvm_intrinsic "x86.avx512.kadd.d" + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: _kadd_mask32 + // LLVM: [[L:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[R:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[RES:%.*]] = call <32 x i1> @llvm.x86.avx512.kadd.d(<32 x i1> [[L]], <32 x i1> [[R]]) + // LLVM: bitcast <32 x i1> [[RES]] to i32 + + // OGCG-LABEL: _kadd_mask32 + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: call <32 x i1> @llvm.x86.avx512.kadd.d + // OGCG: bitcast <32 x i1> {{.*}} to i32 + return _kadd_mask32(A, B); +} + +__mmask64 test_kadd_mask64(__mmask64 A, __mmask64 B) { + // CIR-LABEL: _kadd_mask64 + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.call_llvm_intrinsic "x86.avx512.kadd.q" + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: _kadd_mask64 + // LLVM: [[L:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[R:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[RES:%.*]] = call <64 x i1> @llvm.x86.avx512.kadd.q(<64 x i1> [[L]], <64 x i1> [[R]]) + // LLVM: bitcast <64 x i1> [[RES]] to i64 + + // OGCG-LABEL: _kadd_mask64 + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: call <64 x i1> @llvm.x86.avx512.kadd.q + // OGCG: bitcast <64 x i1> {{.*}} to i64 + return _kadd_mask64(A, B); +} + +__mmask32 test_kand_mask32(__mmask32 A, __mmask32 B) { + // CIR-LABEL: _kand_mask32 + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.binop(and, {{.*}}, {{.*}}) : !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: _kand_mask32 + // LLVM: [[L:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[R:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[RES:%.*]] = and <32 x i1> [[L]], [[R]] + // LLVM: bitcast <32 x i1> [[RES]] to i32 + + // OGCG-LABEL: _kand_mask32 + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: and <32 x i1> + // OGCG: bitcast <32 x i1> {{.*}} to i32 + return _kand_mask32(A, B); +} + +__mmask64 test_kand_mask64(__mmask64 A, __mmask64 B) { + // CIR-LABEL: _kand_mask64 + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.binop(and, {{.*}}, {{.*}}) : !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: _kand_mask64 + // LLVM: [[L:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[R:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[RES:%.*]] = and <64 x i1> [[L]], [[R]] + // LLVM: bitcast <64 x i1> [[RES]] to i64 + + // OGCG-LABEL: _kand_mask64 + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: and <64 x i1> + // OGCG: bitcast <64 x i1> {{.*}} to i64 + return _kand_mask64(A, B); +} + +__mmask32 test_kandn_mask32(__mmask32 A, __mmask32 B) { + // CIR-LABEL: _kandn_mask32 + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.unary(not, {{.*}}) : !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.binop(and, {{.*}}, {{.*}}) : !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: _kandn_mask32 + // LLVM: [[L:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[R:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: xor <32 x i1> [[L]], {{.*}} + // LLVM: and <32 x i1> + // LLVM: bitcast <32 x i1> {{.*}} to i32 + + // OGCG-LABEL: _kandn_mask32 + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: xor <32 x i1> + // OGCG: and <32 x i1> + // OGCG: bitcast <32 x i1> {{.*}} to i32 + return _kandn_mask32(A, B); +} + +__mmask64 test_kandn_mask64(__mmask64 A, __mmask64 B) { + // CIR-LABEL: _kandn_mask64 + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.unary(not, {{.*}}) : !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.binop(and, {{.*}}, {{.*}}) : !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: _kandn_mask64 + // LLVM: [[L:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[R:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: xor <64 x i1> [[L]], {{.*}} + // LLVM: and <64 x i1> + // LLVM: bitcast <64 x i1> {{.*}} to i64 + + // OGCG-LABEL: _kandn_mask64 + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: xor <64 x i1> + // OGCG: and <64 x i1> + // OGCG: bitcast <64 x i1> {{.*}} to i64 + return _kandn_mask64(A, B); +} + +__mmask32 test_kor_mask32(__mmask32 A, __mmask32 B) { + // CIR-LABEL: _kor_mask32 + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.binop(or, {{.*}}, {{.*}}) : !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: _kor_mask32 + // LLVM: [[L:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[R:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: or <32 x i1> [[L]], [[R]] + // LLVM: bitcast <32 x i1> {{.*}} to i32 + + // OGCG-LABEL: _kor_mask32 + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: or <32 x i1> + // OGCG: bitcast <32 x i1> {{.*}} to i32 + return _kor_mask32(A, B); +} + +__mmask64 test_kor_mask64(__mmask64 A, __mmask64 B) { + // CIR-LABEL: _kor_mask64 + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.binop(or, {{.*}}, {{.*}}) : !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: _kor_mask64 + // LLVM: [[L:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[R:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: or <64 x i1> [[L]], [[R]] + // LLVM: bitcast <64 x i1> {{.*}} to i64 + + // OGCG-LABEL: _kor_mask64 + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: or <64 x i1> + // OGCG: bitcast <64 x i1> {{.*}} to i64 + return _kor_mask64(A, B); +} + +__mmask32 test_kxor_mask32(__mmask32 A, __mmask32 B) { + // CIR-LABEL: _kxor_mask32 + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.binop(xor, {{.*}}, {{.*}}) : !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: _kxor_mask32 + // LLVM: [[L:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: [[R:%.*]] = bitcast i32 %{{.*}} to <32 x i1> + // LLVM: xor <32 x i1> [[L]], [[R]] + // LLVM: bitcast <32 x i1> {{.*}} to i32 + + // OGCG-LABEL: _kxor_mask32 + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: xor <32 x i1> + // OGCG: bitcast <32 x i1> {{.*}} to i32 + return _kxor_mask32(A, B); +} + +__mmask64 test_kxor_mask64(__mmask64 A, __mmask64 B) { + // CIR-LABEL: _kxor_mask64 + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.binop(xor, {{.*}}, {{.*}}) : !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: _kxor_mask64 + // LLVM: [[L:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: [[R:%.*]] = bitcast i64 %{{.*}} to <64 x i1> + // LLVM: xor <64 x i1> [[L]], [[R]] + // LLVM: bitcast <64 x i1> {{.*}} to i64 + + // OGCG-LABEL: _kxor_mask64 + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: xor <64 x i1> + // OGCG: bitcast <64 x i1> {{.*}} to i64 + return _kxor_mask64(A, B); +} + +__mmask32 test_knot_mask32(__mmask32 A) { + // CIR-LABEL: _knot_mask32 + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.unary(not, {{.*}}) : !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: _knot_mask32 + // LLVM: bitcast i32 %{{.*}} to <32 x i1> + // LLVM: xor <32 x i1> + // LLVM: bitcast <32 x i1> {{.*}} to i32 + + // OGCG-LABEL: _knot_mask32 + // OGCG: xor <32 x i1> + + return _knot_mask32(A); +} + +__mmask64 test_knot_mask64(__mmask64 A) { + // CIR-LABEL: _knot_mask64 + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.unary(not, {{.*}}) : !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: _knot_mask64 + // LLVM: bitcast i64 %{{.*}} to <64 x i1> + // LLVM: xor <64 x i1> + // LLVM: bitcast <64 x i1> {{.*}} to i64 + + // OGCG-LABEL: _knot_mask64 + // OGCG: xor <64 x i1> + + return _knot_mask64(A); +} + +// Multiple user-level mask helpers inline to this same kmov builtin. +// CIR does not implement any special lowering for those helpers. +// +// Therefore, testing the builtin (__builtin_ia32_kmov*) directly is +// sufficient to cover the CIR lowering behavior. Testing each helper +// individually would add no new CIR paths. + +__mmask32 test_kmov_d(__mmask32 A) { + // CIR-LABEL: test_kmov_d + // CIR: cir.cast bitcast {{.*}} : !u32i -> !cir.vector<32 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<32 x !cir.int<s, 1>> -> !u32i + + // LLVM-LABEL: test_kmov_d + // LLVM: bitcast i32 %{{.*}} to <32 x i1> + // LLVM: bitcast <32 x i1> {{.*}} to i32 + + // OGCG-LABEL: test_kmov_d + // OGCG: bitcast i32 %{{.*}} to <32 x i1> + // OGCG: bitcast <32 x i1> {{.*}} to i32 + + return __builtin_ia32_kmovd(A); +} + +// Multiple user-level mask helpers inline to this same kmov builtin. +// CIR does not implement any special lowering for those helpers. +// +// Therefore, testing the builtin (__builtin_ia32_kmov*) directly is +// sufficient to cover the CIR lowering behavior. Testing each helper +// individually would add no new CIR paths. + +__mmask64 test_kmov_q(__mmask64 A) { + // CIR-LABEL: test_kmov_q + // CIR: cir.cast bitcast {{.*}} : !u64i -> !cir.vector<64 x !cir.int<s, 1>> + // CIR: cir.cast bitcast {{.*}} : !cir.vector<64 x !cir.int<s, 1>> -> !u64i + + // LLVM-LABEL: test_kmov_q + // LLVM: bitcast i64 %{{.*}} to <64 x i1> + // LLVM: bitcast <64 x i1> {{.*}} to i64 + + // OGCG-LABEL: test_kmov_q + // OGCG: bitcast i64 %{{.*}} to <64 x i1> + // OGCG: bitcast <64 x i1> {{.*}} to i64 + + return __builtin_ia32_kmovq(A); +} diff --git a/clang/test/CIR/CodeGen/X86/avx512dq-builtins.c b/clang/test/CIR/CodeGen/X86/avx512dq-builtins.c new file mode 100644 index 0000000000000..21c255e28f3f3 --- /dev/null +++ b/clang/test/CIR/CodeGen/X86/avx512dq-builtins.c @@ -0,0 +1,213 @@ + // RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512dq -fclangir -emit-cir -o %t.cir -Wall -Werror + // RUN: FileCheck --check-prefix=CIR --input-file=%t.cir %s + // RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512dq -fclangir -emit-llvm -o %t.ll -Wall -Werror + // RUN: FileCheck... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/169185 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
