[libc-commits] [clang] [compiler-rt] [flang] [libc] [libcxx] [lld] [lldb] [llvm] [mlir] Optimize __insert_with_sentinel Function in std::vector (PR #113727)
via libc-commits
libc-commits at lists.llvm.org
Sat Oct 26 08:39:30 PDT 2024
Martin =?utf-8?q?Storsjö?= <martin at martin.st>,Thomas Fransham
<tfransham at gmail.com>,davidtrevelyan
<davidtrevelyan at users.noreply.github.com>,
Andrzej =?utf-8?q?Warzyński?= <andrzej.warzynski at arm.com>,Louis Dionne
<ldionne.2 at gmail.com>,Alex =?utf-8?q?Rønne?= Petersen <alex at alexrp.com>,lntue
<lntue at google.com>,Shih-Po Hung <shihpo.hung at sifive.com>,Peng Liu
<winner245 at hotmail.com>,Peng Liu <winner245 at hotmail.com>
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/113727 at github.com>
github-actions[bot] wrote:
<!--LLVM CODE FORMAT COMMENT: {clang-format}-->
:warning: C/C++ code formatter, clang-format found issues in your code. :warning:
<details>
<summary>
You can test this locally with the following command:
</summary>
``````````bash
git-clang-format --diff 8c4bc1e75de27adfbaead34b895b0efbaf17bd02 3b5b692134d48ce4ebc2f21b9a4b569d24ddf9a3 --extensions ,cpp,cppm,c,h -- clang/test/Format/error-unfound-files.cpp flang/include/flang/Optimizer/Transforms/CUFCommon.h flang/lib/Optimizer/Transforms/CUFCommon.cpp libcxx/include/__locale_dir/locale_base_api/freebsd.h clang/include/clang/Lex/Preprocessor.h clang/include/clang/Serialization/ASTBitCodes.h clang/lib/Basic/Targets/WebAssembly.cpp clang/lib/CodeGen/CodeGenFunction.cpp clang/lib/Lex/HeaderSearch.cpp clang/lib/Serialization/ASTWriter.cpp clang/test/CodeGen/rtsan_attribute_inserted.c clang/test/CodeGen/rtsan_no_attribute_sanitizer_disabled.c clang/test/Modules/no-external-type-id.cppm clang/test/Preprocessor/wasm-target-features.c clang/tools/clang-format/ClangFormat.cpp compiler-rt/lib/rtsan/tests/rtsan_test_functional.cpp flang/lib/Optimizer/Transforms/CUFAddConstructor.cpp libc/src/math/generic/atan2.cpp libc/src/math/generic/cbrt.cpp libc/src/math/generic/cbrtf.cpp libc/src/math/generic/log.cpp libc/src/math/generic/log10.cpp libc/src/math/generic/log10f.cpp libc/src/math/generic/log1p.cpp libc/src/math/generic/log2.cpp libc/src/math/generic/log2f.cpp libc/src/math/generic/logf.cpp libc/src/math/generic/pow.cpp libc/src/math/generic/powf.cpp libc/src/math/generic/sin.cpp libc/src/math/generic/tan.cpp libc/test/src/math/cbrt_test.cpp libc/test/src/math/smoke/HypotTest.h libc/test/src/math/smoke/acosf_test.cpp libc/test/src/math/smoke/acoshf_test.cpp libc/test/src/math/smoke/asinf_test.cpp libc/test/src/math/smoke/asinhf_test.cpp libc/test/src/math/smoke/atan2_test.cpp libc/test/src/math/smoke/atanf_test.cpp libc/test/src/math/smoke/atanhf_test.cpp libc/test/src/math/smoke/cbrt_test.cpp libc/test/src/math/smoke/cbrtf_test.cpp libc/test/src/math/smoke/cos_test.cpp libc/test/src/math/smoke/cosf_test.cpp libc/test/src/math/smoke/coshf_test.cpp libc/test/src/math/smoke/cospif_test.cpp libc/test/src/math/smoke/erff_test.cpp libc/test/src/math/smoke/exp10_test.cpp libc/test/src/math/smoke/exp10f_test.cpp libc/test/src/math/smoke/exp2_test.cpp libc/test/src/math/smoke/exp2f_test.cpp libc/test/src/math/smoke/exp2m1f_test.cpp libc/test/src/math/smoke/exp_test.cpp libc/test/src/math/smoke/expf_test.cpp libc/test/src/math/smoke/expm1_test.cpp libc/test/src/math/smoke/expm1f_test.cpp libc/test/src/math/smoke/hypotf_test.cpp libc/test/src/math/smoke/log10_test.cpp libc/test/src/math/smoke/log10f_test.cpp libc/test/src/math/smoke/log1p_test.cpp libc/test/src/math/smoke/log1pf_test.cpp libc/test/src/math/smoke/log2_test.cpp libc/test/src/math/smoke/log2f_test.cpp libc/test/src/math/smoke/log_test.cpp libc/test/src/math/smoke/logf_test.cpp libc/test/src/math/smoke/pow_test.cpp libc/test/src/math/smoke/powf_test.cpp libc/test/src/math/smoke/sin_test.cpp libc/test/src/math/smoke/sinf_test.cpp libc/test/src/math/smoke/sinhf_test.cpp libc/test/src/math/smoke/sinpif_test.cpp libc/test/src/math/smoke/tan_test.cpp libc/test/src/math/smoke/tanf_test.cpp libc/test/src/math/smoke/tanhf_test.cpp libcxx/include/__locale_dir/locale_base_api.h libcxx/include/__vector/vector.h libcxx/include/version libcxx/test/std/containers/sequences/vector/vector.capacity/shrink_to_fit.pass.cpp libcxx/test/std/containers/sequences/vector/vector.modifiers/insert_iter_iter_iter.pass.cpp libcxx/test/std/language.support/support.limits/support.limits.general/optional.version.compile.pass.cpp libcxx/test/std/language.support/support.limits/support.limits.general/variant.version.compile.pass.cpp libcxx/test/std/language.support/support.limits/support.limits.general/version.version.compile.pass.cpp libcxx/test/support/test_macros.h lldb/source/Plugins/UnwindAssembly/InstEmulation/UnwindAssemblyInstEmulation.cpp llvm/include/llvm/ADT/StringRef.h llvm/include/llvm/Analysis/TargetLibraryInfo.h llvm/include/llvm/Bitcode/LLVMBitCodes.h llvm/include/llvm/Transforms/Vectorize/SandboxVectorizer/Legality.h llvm/lib/Bitcode/Reader/BitcodeReader.cpp llvm/lib/Bitcode/Writer/BitcodeWriter.cpp llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp llvm/lib/IR/Verifier.cpp llvm/lib/Support/StringRef.cpp llvm/lib/Target/SystemZ/SystemZFrameLowering.cpp llvm/lib/Target/WebAssembly/WebAssemblyFixFunctionBitcasts.cpp llvm/lib/Target/WebAssembly/WebAssemblyTargetMachine.cpp llvm/lib/Target/X86/X86TargetTransformInfo.cpp llvm/lib/Target/X86/X86TargetTransformInfo.h llvm/lib/Transforms/Instrumentation/RealtimeSanitizer.cpp llvm/lib/Transforms/Utils/CodeExtractor.cpp llvm/lib/Transforms/Vectorize/LoopVectorize.cpp llvm/lib/Transforms/Vectorize/SandboxVectorizer/Legality.cpp llvm/lib/Transforms/Vectorize/SandboxVectorizer/Passes/BottomUpVec.cpp llvm/lib/Transforms/Vectorize/VPlan.h llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp llvm/lib/Transforms/Vectorize/VPlanUnroll.cpp llvm/lib/Transforms/Vectorize/VPlanValue.h llvm/unittests/Transforms/Vectorize/SandboxVectorizer/LegalityTest.cpp mlir/lib/Conversion/GPUCommon/OpToFuncCallLowering.h mlir/lib/Conversion/SPIRVToLLVM/SPIRVToLLVM.cpp mlir/lib/Dialect/GPU/Transforms/DecomposeMemRefs.cpp mlir/lib/Dialect/MemRef/IR/MemRefOps.cpp mlir/lib/Dialect/MemRef/Transforms/ExpandOps.cpp mlir/lib/Dialect/MemRef/Transforms/ExpandStridedMetadata.cpp mlir/lib/Dialect/Vector/IR/VectorOps.cpp mlir/lib/Dialect/Vector/Transforms/VectorTransferOpTransforms.cpp mlir/lib/Transforms/Utils/DialectConversion.cpp libcxx/include/__locale_dir/locale_base_api/apple.h
``````````
</details>
<details>
<summary>
View the diff from clang-format here.
</summary>
``````````diff
diff --git a/libcxx/include/__vector/vector.h b/libcxx/include/__vector/vector.h
index 196c947e23..02f91b537c 100644
--- a/libcxx/include/__vector/vector.h
+++ b/libcxx/include/__vector/vector.h
@@ -1352,8 +1352,7 @@ vector<_Tp, _Allocator>::insert(const_iterator __position, _InputIterator __firs
template <class _Tp, class _Allocator>
template <class _InputIterator, class _Sentinel>
_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI typename vector<_Tp, _Allocator>::iterator
-vector<_Tp, _Allocator>::__insert_with_sentinel(const_iterator __position,
- _InputIterator __first, _Sentinel __last) {
+vector<_Tp, _Allocator>::__insert_with_sentinel(const_iterator __position, _InputIterator __first, _Sentinel __last) {
difference_type __off = __position - begin();
pointer __p = this->__begin_ + __off;
allocator_type& __a = this->__alloc();
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index bae223243b..9abc2051bf 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -2293,143 +2293,221 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
// 256-bit wide vectors.
static const TypeConversionCostKindTblEntry AVX512FConversionTbl[] = {
- { ISD::FP_EXTEND, MVT::v8f64, MVT::v8f32, { 1, 1, 1, 1 } },
- { ISD::FP_EXTEND, MVT::v8f64, MVT::v16f32, { 3, 1, 1, 1 } },
- { ISD::FP_EXTEND, MVT::v16f64, MVT::v16f32, { 4, 1, 1, 1 } }, // 2*vcvtps2pd+vextractf64x4
- { ISD::FP_EXTEND, MVT::v16f32, MVT::v16f16, { 1, 1, 1, 1 } }, // vcvtph2ps
- { ISD::FP_EXTEND, MVT::v8f64, MVT::v8f16, { 2, 1, 1, 1 } }, // vcvtph2ps+vcvtps2pd
- { ISD::FP_ROUND, MVT::v8f32, MVT::v8f64, { 1, 1, 1, 1 } },
- { ISD::FP_ROUND, MVT::v16f16, MVT::v16f32, { 1, 1, 1, 1 } }, // vcvtps2ph
-
- { ISD::TRUNCATE, MVT::v2i1, MVT::v2i8, { 3, 1, 1, 1 } }, // sext+vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v4i1, MVT::v4i8, { 3, 1, 1, 1 } }, // sext+vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v8i1, MVT::v8i8, { 3, 1, 1, 1 } }, // sext+vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v16i1, MVT::v16i8, { 3, 1, 1, 1 } }, // sext+vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v2i1, MVT::v2i16, { 3, 1, 1, 1 } }, // sext+vpsllq+vptestmq
- { ISD::TRUNCATE, MVT::v4i1, MVT::v4i16, { 3, 1, 1, 1 } }, // sext+vpsllq+vptestmq
- { ISD::TRUNCATE, MVT::v8i1, MVT::v8i16, { 3, 1, 1, 1 } }, // sext+vpsllq+vptestmq
- { ISD::TRUNCATE, MVT::v16i1, MVT::v16i16, { 3, 1, 1, 1 } }, // sext+vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v2i1, MVT::v2i32, { 2, 1, 1, 1 } }, // zmm vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v4i1, MVT::v4i32, { 2, 1, 1, 1 } }, // zmm vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v8i1, MVT::v8i32, { 2, 1, 1, 1 } }, // zmm vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v16i1, MVT::v16i32, { 2, 1, 1, 1 } }, // vpslld+vptestmd
- { ISD::TRUNCATE, MVT::v2i1, MVT::v2i64, { 2, 1, 1, 1 } }, // zmm vpsllq+vptestmq
- { ISD::TRUNCATE, MVT::v4i1, MVT::v4i64, { 2, 1, 1, 1 } }, // zmm vpsllq+vptestmq
- { ISD::TRUNCATE, MVT::v8i1, MVT::v8i64, { 2, 1, 1, 1 } }, // vpsllq+vptestmq
- { ISD::TRUNCATE, MVT::v2i8, MVT::v2i32, { 2, 1, 1, 1 } }, // vpmovdb
- { ISD::TRUNCATE, MVT::v4i8, MVT::v4i32, { 2, 1, 1, 1 } }, // vpmovdb
- { ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, { 2, 1, 1, 1 } }, // vpmovdb
- { ISD::TRUNCATE, MVT::v32i8, MVT::v16i32, { 2, 1, 1, 1 } }, // vpmovdb
- { ISD::TRUNCATE, MVT::v64i8, MVT::v16i32, { 2, 1, 1, 1 } }, // vpmovdb
- { ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, { 2, 1, 1, 1 } }, // vpmovdw
- { ISD::TRUNCATE, MVT::v32i16, MVT::v16i32, { 2, 1, 1, 1 } }, // vpmovdw
- { ISD::TRUNCATE, MVT::v2i8, MVT::v2i64, { 2, 1, 1, 1 } }, // vpmovqb
- { ISD::TRUNCATE, MVT::v2i16, MVT::v2i64, { 1, 1, 1, 1 } }, // vpshufb
- { ISD::TRUNCATE, MVT::v8i8, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqb
- { ISD::TRUNCATE, MVT::v16i8, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqb
- { ISD::TRUNCATE, MVT::v32i8, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqb
- { ISD::TRUNCATE, MVT::v64i8, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqb
- { ISD::TRUNCATE, MVT::v8i16, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqw
- { ISD::TRUNCATE, MVT::v16i16, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqw
- { ISD::TRUNCATE, MVT::v32i16, MVT::v8i64, { 2, 1, 1, 1 } }, // vpmovqw
- { ISD::TRUNCATE, MVT::v8i32, MVT::v8i64, { 1, 1, 1, 1 } }, // vpmovqd
- { ISD::TRUNCATE, MVT::v4i32, MVT::v4i64, { 1, 1, 1, 1 } }, // zmm vpmovqd
- { ISD::TRUNCATE, MVT::v16i8, MVT::v16i64, { 5, 1, 1, 1 } },// 2*vpmovqd+concat+vpmovdb
-
- { ISD::TRUNCATE, MVT::v16i8, MVT::v16i16, { 3, 1, 1, 1 } }, // extend to v16i32
- { ISD::TRUNCATE, MVT::v32i8, MVT::v32i16, { 8, 1, 1, 1 } },
- { ISD::TRUNCATE, MVT::v64i8, MVT::v32i16, { 8, 1, 1, 1 } },
-
- // Sign extend is zmm vpternlogd+vptruncdb.
- // Zero extend is zmm broadcast load+vptruncdw.
- { ISD::SIGN_EXTEND, MVT::v2i8, MVT::v2i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v2i8, MVT::v2i1, { 4, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v4i8, MVT::v4i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v4i8, MVT::v4i1, { 4, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v8i8, MVT::v8i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v8i8, MVT::v8i1, { 4, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v16i8, MVT::v16i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v16i8, MVT::v16i1, { 4, 1, 1, 1 } },
-
- // Sign extend is zmm vpternlogd+vptruncdw.
- // Zero extend is zmm vpternlogd+vptruncdw+vpsrlw.
- { ISD::SIGN_EXTEND, MVT::v2i16, MVT::v2i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v2i16, MVT::v2i1, { 4, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v4i16, MVT::v4i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v4i16, MVT::v4i1, { 4, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v8i16, MVT::v8i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v8i16, MVT::v8i1, { 4, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i1, { 3, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v16i16, MVT::v16i1, { 4, 1, 1, 1 } },
-
- { ISD::SIGN_EXTEND, MVT::v2i32, MVT::v2i1, { 1, 1, 1, 1 } }, // zmm vpternlogd
- { ISD::ZERO_EXTEND, MVT::v2i32, MVT::v2i1, { 2, 1, 1, 1 } }, // zmm vpternlogd+psrld
- { ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i1, { 1, 1, 1, 1 } }, // zmm vpternlogd
- { ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i1, { 2, 1, 1, 1 } }, // zmm vpternlogd+psrld
- { ISD::SIGN_EXTEND, MVT::v8i32, MVT::v8i1, { 1, 1, 1, 1 } }, // zmm vpternlogd
- { ISD::ZERO_EXTEND, MVT::v8i32, MVT::v8i1, { 2, 1, 1, 1 } }, // zmm vpternlogd+psrld
- { ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i1, { 1, 1, 1, 1 } }, // zmm vpternlogq
- { ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i1, { 2, 1, 1, 1 } }, // zmm vpternlogq+psrlq
- { ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i1, { 1, 1, 1, 1 } }, // zmm vpternlogq
- { ISD::ZERO_EXTEND, MVT::v4i64, MVT::v4i1, { 2, 1, 1, 1 } }, // zmm vpternlogq+psrlq
-
- { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i1, { 1, 1, 1, 1 } }, // vpternlogd
- { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i1, { 2, 1, 1, 1 } }, // vpternlogd+psrld
- { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i1, { 1, 1, 1, 1 } }, // vpternlogq
- { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i1, { 2, 1, 1, 1 } }, // vpternlogq+psrlq
-
- { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8, { 1, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8, { 1, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i16, { 1, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i16, { 1, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i8, { 1, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i8, { 1, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i16, { 1, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i16, { 1, 1, 1, 1 } },
- { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i32, { 1, 1, 1, 1 } },
- { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i32, { 1, 1, 1, 1 } },
-
- { ISD::SIGN_EXTEND, MVT::v32i16, MVT::v32i8, { 3, 1, 1, 1 } }, // FIXME: May not be right
- { ISD::ZERO_EXTEND, MVT::v32i16, MVT::v32i8, { 3, 1, 1, 1 } }, // FIXME: May not be right
-
- { ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i1, { 4, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i1, { 3, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v8f64, MVT::v16i8, { 2, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i8, { 1, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i16, { 2, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i16, { 1, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i32, { 1, 1, 1, 1 } },
- { ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i32, { 1, 1, 1, 1 } },
-
- { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i1, { 4, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i1, { 3, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v8f64, MVT::v16i8, { 2, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i8, { 1, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i16, { 2, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i16, { 1, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i32, { 1, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i32, { 1, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i64, {26, 1, 1, 1 } },
- { ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i64, { 5, 1, 1, 1 } },
-
- { ISD::FP_TO_SINT, MVT::v16i8, MVT::v16f32, { 2, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v16i8, MVT::v16f64, { 7, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v32i8, MVT::v32f64, {15, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v64i8, MVT::v64f32, {11, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v64i8, MVT::v64f64, {31, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v8i16, MVT::v8f64, { 3, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v16i16, MVT::v16f64, { 7, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v32i16, MVT::v32f32, { 5, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v32i16, MVT::v32f64, {15, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v8i32, MVT::v8f64, { 1, 1, 1, 1 } },
- { ISD::FP_TO_SINT, MVT::v16i32, MVT::v16f64, { 3, 1, 1, 1 } },
-
- { ISD::FP_TO_UINT, MVT::v8i32, MVT::v8f64, { 1, 1, 1, 1 } },
- { ISD::FP_TO_UINT, MVT::v8i16, MVT::v8f64, { 3, 1, 1, 1 } },
- { ISD::FP_TO_UINT, MVT::v8i8, MVT::v8f64, { 3, 1, 1, 1 } },
- { ISD::FP_TO_UINT, MVT::v16i32, MVT::v16f32, { 1, 1, 1, 1 } },
- { ISD::FP_TO_UINT, MVT::v16i16, MVT::v16f32, { 3, 1, 1, 1 } },
- { ISD::FP_TO_UINT, MVT::v16i8, MVT::v16f32, { 3, 1, 1, 1 } },
+ {ISD::FP_EXTEND, MVT::v8f64, MVT::v8f32, {1, 1, 1, 1}},
+ {ISD::FP_EXTEND, MVT::v8f64, MVT::v16f32, {3, 1, 1, 1}},
+ {ISD::FP_EXTEND,
+ MVT::v16f64,
+ MVT::v16f32,
+ {4, 1, 1, 1}}, // 2*vcvtps2pd+vextractf64x4
+ {ISD::FP_EXTEND, MVT::v16f32, MVT::v16f16, {1, 1, 1, 1}}, // vcvtph2ps
+ {ISD::FP_EXTEND,
+ MVT::v8f64,
+ MVT::v8f16,
+ {2, 1, 1, 1}}, // vcvtph2ps+vcvtps2pd
+ {ISD::FP_ROUND, MVT::v8f32, MVT::v8f64, {1, 1, 1, 1}},
+ {ISD::FP_ROUND, MVT::v16f16, MVT::v16f32, {1, 1, 1, 1}}, // vcvtps2ph
+
+ {ISD::TRUNCATE,
+ MVT::v2i1,
+ MVT::v2i8,
+ {3, 1, 1, 1}}, // sext+vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v4i1,
+ MVT::v4i8,
+ {3, 1, 1, 1}}, // sext+vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v8i1,
+ MVT::v8i8,
+ {3, 1, 1, 1}}, // sext+vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v16i1,
+ MVT::v16i8,
+ {3, 1, 1, 1}}, // sext+vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v2i1,
+ MVT::v2i16,
+ {3, 1, 1, 1}}, // sext+vpsllq+vptestmq
+ {ISD::TRUNCATE,
+ MVT::v4i1,
+ MVT::v4i16,
+ {3, 1, 1, 1}}, // sext+vpsllq+vptestmq
+ {ISD::TRUNCATE,
+ MVT::v8i1,
+ MVT::v8i16,
+ {3, 1, 1, 1}}, // sext+vpsllq+vptestmq
+ {ISD::TRUNCATE,
+ MVT::v16i1,
+ MVT::v16i16,
+ {3, 1, 1, 1}}, // sext+vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v2i1,
+ MVT::v2i32,
+ {2, 1, 1, 1}}, // zmm vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v4i1,
+ MVT::v4i32,
+ {2, 1, 1, 1}}, // zmm vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v8i1,
+ MVT::v8i32,
+ {2, 1, 1, 1}}, // zmm vpslld+vptestmd
+ {ISD::TRUNCATE, MVT::v16i1, MVT::v16i32, {2, 1, 1, 1}}, // vpslld+vptestmd
+ {ISD::TRUNCATE,
+ MVT::v2i1,
+ MVT::v2i64,
+ {2, 1, 1, 1}}, // zmm vpsllq+vptestmq
+ {ISD::TRUNCATE,
+ MVT::v4i1,
+ MVT::v4i64,
+ {2, 1, 1, 1}}, // zmm vpsllq+vptestmq
+ {ISD::TRUNCATE, MVT::v8i1, MVT::v8i64, {2, 1, 1, 1}}, // vpsllq+vptestmq
+ {ISD::TRUNCATE, MVT::v2i8, MVT::v2i32, {2, 1, 1, 1}}, // vpmovdb
+ {ISD::TRUNCATE, MVT::v4i8, MVT::v4i32, {2, 1, 1, 1}}, // vpmovdb
+ {ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, {2, 1, 1, 1}}, // vpmovdb
+ {ISD::TRUNCATE, MVT::v32i8, MVT::v16i32, {2, 1, 1, 1}}, // vpmovdb
+ {ISD::TRUNCATE, MVT::v64i8, MVT::v16i32, {2, 1, 1, 1}}, // vpmovdb
+ {ISD::TRUNCATE, MVT::v16i16, MVT::v16i32, {2, 1, 1, 1}}, // vpmovdw
+ {ISD::TRUNCATE, MVT::v32i16, MVT::v16i32, {2, 1, 1, 1}}, // vpmovdw
+ {ISD::TRUNCATE, MVT::v2i8, MVT::v2i64, {2, 1, 1, 1}}, // vpmovqb
+ {ISD::TRUNCATE, MVT::v2i16, MVT::v2i64, {1, 1, 1, 1}}, // vpshufb
+ {ISD::TRUNCATE, MVT::v8i8, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqb
+ {ISD::TRUNCATE, MVT::v16i8, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqb
+ {ISD::TRUNCATE, MVT::v32i8, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqb
+ {ISD::TRUNCATE, MVT::v64i8, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqb
+ {ISD::TRUNCATE, MVT::v8i16, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqw
+ {ISD::TRUNCATE, MVT::v16i16, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqw
+ {ISD::TRUNCATE, MVT::v32i16, MVT::v8i64, {2, 1, 1, 1}}, // vpmovqw
+ {ISD::TRUNCATE, MVT::v8i32, MVT::v8i64, {1, 1, 1, 1}}, // vpmovqd
+ {ISD::TRUNCATE, MVT::v4i32, MVT::v4i64, {1, 1, 1, 1}}, // zmm vpmovqd
+ {ISD::TRUNCATE,
+ MVT::v16i8,
+ MVT::v16i64,
+ {5, 1, 1, 1}}, // 2*vpmovqd+concat+vpmovdb
+
+ {ISD::TRUNCATE,
+ MVT::v16i8,
+ MVT::v16i16,
+ {3, 1, 1, 1}}, // extend to v16i32
+ {ISD::TRUNCATE, MVT::v32i8, MVT::v32i16, {8, 1, 1, 1}},
+ {ISD::TRUNCATE, MVT::v64i8, MVT::v32i16, {8, 1, 1, 1}},
+
+ // Sign extend is zmm vpternlogd+vptruncdb.
+ // Zero extend is zmm broadcast load+vptruncdw.
+ {ISD::SIGN_EXTEND, MVT::v2i8, MVT::v2i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v2i8, MVT::v2i1, {4, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v4i8, MVT::v4i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v4i8, MVT::v4i1, {4, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v8i8, MVT::v8i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v8i8, MVT::v8i1, {4, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v16i8, MVT::v16i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v16i8, MVT::v16i1, {4, 1, 1, 1}},
+
+ // Sign extend is zmm vpternlogd+vptruncdw.
+ // Zero extend is zmm vpternlogd+vptruncdw+vpsrlw.
+ {ISD::SIGN_EXTEND, MVT::v2i16, MVT::v2i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v2i16, MVT::v2i1, {4, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v4i16, MVT::v4i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v4i16, MVT::v4i1, {4, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v8i16, MVT::v8i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v8i16, MVT::v8i1, {4, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i1, {3, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v16i16, MVT::v16i1, {4, 1, 1, 1}},
+
+ {ISD::SIGN_EXTEND, MVT::v2i32, MVT::v2i1, {1, 1, 1, 1}}, // zmm vpternlogd
+ {ISD::ZERO_EXTEND,
+ MVT::v2i32,
+ MVT::v2i1,
+ {2, 1, 1, 1}}, // zmm vpternlogd+psrld
+ {ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i1, {1, 1, 1, 1}}, // zmm vpternlogd
+ {ISD::ZERO_EXTEND,
+ MVT::v4i32,
+ MVT::v4i1,
+ {2, 1, 1, 1}}, // zmm vpternlogd+psrld
+ {ISD::SIGN_EXTEND, MVT::v8i32, MVT::v8i1, {1, 1, 1, 1}}, // zmm vpternlogd
+ {ISD::ZERO_EXTEND,
+ MVT::v8i32,
+ MVT::v8i1,
+ {2, 1, 1, 1}}, // zmm vpternlogd+psrld
+ {ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i1, {1, 1, 1, 1}}, // zmm vpternlogq
+ {ISD::ZERO_EXTEND,
+ MVT::v2i64,
+ MVT::v2i1,
+ {2, 1, 1, 1}}, // zmm vpternlogq+psrlq
+ {ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i1, {1, 1, 1, 1}}, // zmm vpternlogq
+ {ISD::ZERO_EXTEND,
+ MVT::v4i64,
+ MVT::v4i1,
+ {2, 1, 1, 1}}, // zmm vpternlogq+psrlq
+
+ {ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i1, {1, 1, 1, 1}}, // vpternlogd
+ {ISD::ZERO_EXTEND,
+ MVT::v16i32,
+ MVT::v16i1,
+ {2, 1, 1, 1}}, // vpternlogd+psrld
+ {ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i1, {1, 1, 1, 1}}, // vpternlogq
+ {ISD::ZERO_EXTEND,
+ MVT::v8i64,
+ MVT::v8i1,
+ {2, 1, 1, 1}}, // vpternlogq+psrlq
+
+ {ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8, {1, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8, {1, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i16, {1, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i16, {1, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i8, {1, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i8, {1, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i16, {1, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i16, {1, 1, 1, 1}},
+ {ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i32, {1, 1, 1, 1}},
+ {ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i32, {1, 1, 1, 1}},
+
+ {ISD::SIGN_EXTEND,
+ MVT::v32i16,
+ MVT::v32i8,
+ {3, 1, 1, 1}}, // FIXME: May not be right
+ {ISD::ZERO_EXTEND,
+ MVT::v32i16,
+ MVT::v32i8,
+ {3, 1, 1, 1}}, // FIXME: May not be right
+
+ {ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i1, {4, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i1, {3, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v8f64, MVT::v16i8, {2, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i8, {1, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i16, {2, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i16, {1, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v8f64, MVT::v8i32, {1, 1, 1, 1}},
+ {ISD::SINT_TO_FP, MVT::v16f32, MVT::v16i32, {1, 1, 1, 1}},
+
+ {ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i1, {4, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i1, {3, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v8f64, MVT::v16i8, {2, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i8, {1, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i16, {2, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i16, {1, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i32, {1, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v16f32, MVT::v16i32, {1, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v8f32, MVT::v8i64, {26, 1, 1, 1}},
+ {ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i64, {5, 1, 1, 1}},
+
+ {ISD::FP_TO_SINT, MVT::v16i8, MVT::v16f32, {2, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v16i8, MVT::v16f64, {7, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v32i8, MVT::v32f64, {15, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v64i8, MVT::v64f32, {11, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v64i8, MVT::v64f64, {31, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v8i16, MVT::v8f64, {3, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v16i16, MVT::v16f64, {7, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v32i16, MVT::v32f32, {5, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v32i16, MVT::v32f64, {15, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v8i32, MVT::v8f64, {1, 1, 1, 1}},
+ {ISD::FP_TO_SINT, MVT::v16i32, MVT::v16f64, {3, 1, 1, 1}},
+
+ {ISD::FP_TO_UINT, MVT::v8i32, MVT::v8f64, {1, 1, 1, 1}},
+ {ISD::FP_TO_UINT, MVT::v8i16, MVT::v8f64, {3, 1, 1, 1}},
+ {ISD::FP_TO_UINT, MVT::v8i8, MVT::v8f64, {3, 1, 1, 1}},
+ {ISD::FP_TO_UINT, MVT::v16i32, MVT::v16f32, {1, 1, 1, 1}},
+ {ISD::FP_TO_UINT, MVT::v16i16, MVT::v16f32, {3, 1, 1, 1}},
+ {ISD::FP_TO_UINT, MVT::v16i8, MVT::v16f32, {3, 1, 1, 1}},
};
static const TypeConversionCostKindTblEntry AVX512BWVLConversionTbl[] {
@@ -2977,14 +3055,17 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
};
static const TypeConversionCostKindTblEntry F16ConversionTbl[] = {
- { ISD::FP_ROUND, MVT::f16, MVT::f32, { 1, 1, 1, 1 } },
- { ISD::FP_ROUND, MVT::v8f16, MVT::v8f32, { 1, 1, 1, 1 } },
- { ISD::FP_ROUND, MVT::v4f16, MVT::v4f32, { 1, 1, 1, 1 } },
- { ISD::FP_EXTEND, MVT::f32, MVT::f16, { 1, 1, 1, 1 } },
- { ISD::FP_EXTEND, MVT::f64, MVT::f16, { 2, 1, 1, 1 } }, // vcvtph2ps+vcvtps2pd
- { ISD::FP_EXTEND, MVT::v8f32, MVT::v8f16, { 1, 1, 1, 1 } },
- { ISD::FP_EXTEND, MVT::v4f32, MVT::v4f16, { 1, 1, 1, 1 } },
- { ISD::FP_EXTEND, MVT::v4f64, MVT::v4f16, { 2, 1, 1, 1 } }, // vcvtph2ps+vcvtps2pd
+ {ISD::FP_ROUND, MVT::f16, MVT::f32, {1, 1, 1, 1}},
+ {ISD::FP_ROUND, MVT::v8f16, MVT::v8f32, {1, 1, 1, 1}},
+ {ISD::FP_ROUND, MVT::v4f16, MVT::v4f32, {1, 1, 1, 1}},
+ {ISD::FP_EXTEND, MVT::f32, MVT::f16, {1, 1, 1, 1}},
+ {ISD::FP_EXTEND, MVT::f64, MVT::f16, {2, 1, 1, 1}}, // vcvtph2ps+vcvtps2pd
+ {ISD::FP_EXTEND, MVT::v8f32, MVT::v8f16, {1, 1, 1, 1}},
+ {ISD::FP_EXTEND, MVT::v4f32, MVT::v4f16, {1, 1, 1, 1}},
+ {ISD::FP_EXTEND,
+ MVT::v4f64,
+ MVT::v4f16,
+ {2, 1, 1, 1}}, // vcvtph2ps+vcvtps2pd
};
// Attempt to map directly to (simple) MVT types to let us match custom entries.
``````````
</details>
https://github.com/llvm/llvm-project/pull/113727
More information about the libc-commits
mailing list