[llvm] r209123 - SDAG: Legalize vector BSWAP into a shuffle if the shuffle is legal but the bswap not.
Benjamin Kramer
benny.kra at gmail.com
Mon May 19 09:47:32 PDT 2014
On 19.05.2014, at 18:44, Alexander Potapenko <glider at google.com> wrote:
> This broke Chromium compilation w/ThreadSanitizer on one of our
> buildbots. Let me know if you need a repro.
Can you send me preprocessed source or IR?
- Ben
>
> FAILED: /usr/local/google/home/dtoolsbot/llvm-buildbot/slave/linux-chrome-tsan/build/clang_build/bin/clang
> -MMD -MF obj/third_party/mesa/src/src/mesa/main/mesa.pack.o.d
> '-DMAPI_ABI_HEADER="glapi_mapi_tmp_shared.h"' '-DPACKAGE_NAME="Mesa"'
> '-DPACKAGE_TARNAME="mesa"' '-DPACKAGE_VERSION="9.0.3"'
> '-DPACKAGE_STRING="Mesa\ 9.0.3"'
> '-DPACKAGE_BUGREPORT="https://bugs.freedesktop.org/enter_bug.cgi\?product=Mesa"'
> '-DPACKAGE_URL=""' '-DPACKAGE="mesa"' '-DVERSION="9.0.3"'
> -DSTDC_HEADERS=1 -DHAVE_SYS_TYPES_H=1 -DHAVE_SYS_STAT_H=1
> -DHAVE_STDLIB_H=1 -DHAVE_STRING_H=1 -DHAVE_MEMORY_H=1
> -DHAVE_STRINGS_H=1 -DHAVE_INTTYPES_H=1 -DHAVE_STDINT_H=1
> -DHAVE_DLFCN_H=1 '-DLT_OBJDIR=".libs/"' -DYYTEXT_POINTER=1
> -DHAVE_LIBEXPAT=1 -DHAVE_LIBXCB_DRI2=1 -DFEATURE_GL=1
> -DMAPI_MODE_GLAPI -DIN_DRI_DRIVER -DUSE_XCB -DGLX_INDIRECT_RENDERING
> -DGLX_DIRECT_RENDERING -DUSE_EXTERNAL_DXTN_LIB=1 -DIN_DRI_DRIVER
> -DHAVE_ALIAS -DHAVE_MINCORE -DHAVE_LIBUDEV -D_GLAPI_NO_EXPORTS
> -DV8_DEPRECATION_WARNINGS -DBLINK_SCALE_FILTERS_AT_RECORD_TIME
> -D_FILE_OFFSET_BITS=64 -DNO_TCMALLOC -DDISABLE_NACL -D_GNU_SOURCE
> -DHAVE_DLOPEN -DHAVE_PTHREAD=1 -DHAVE_UNISTD_H=1 -DHAVE_POSIX_MEMALIGN
> -DCHROMIUM_BUILD -DCR_CLANG_REVISION=206824 -DTOOLKIT_VIEWS=1
> -DUI_COMPOSITOR_IMAGE_TRANSPORT -DUSE_AURA=1 -DUSE_CAIRO=1
> -DUSE_GLIB=1 -DUSE_DEFAULT_RENDER_THEME=1 -DUSE_LIBJPEG_TURBO=1
> -DUSE_X11=1 -DUSE_CLIPBOARD_AURAX11=1 -DENABLE_ONE_CLICK_SIGNIN
> -DUSE_XI2_MT=2 -DENABLE_REMOTING=1 -DENABLE_WEBRTC=1
> -DENABLE_PEPPER_CDMS -DENABLE_CONFIGURATION_POLICY
> -DENABLE_NOTIFICATIONS -DUSE_UDEV -DENABLE_EGLIMAGE=1
> -DENABLE_TASK_MANAGER=1 -DENABLE_EXTENSIONS=1
> -DENABLE_PLUGIN_INSTALLATION=1 -DENABLE_PLUGINS=1
> -DENABLE_SESSION_SERVICE=1 -DENABLE_THEMES=1
> -DENABLE_AUTOFILL_DIALOG=1 -DENABLE_BACKGROUND=1 -DENABLE_GOOGLE_NOW=1
> -DCLD_VERSION=2 -DENABLE_FULL_PRINTING=1 -DENABLE_PRINTING=1
> -DENABLE_SPELLCHECK=1 -DENABLE_CAPTIVE_PORTAL_DETECTION=1
> -DENABLE_APP_LIST=1 -DENABLE_SETTINGS_APP=1 -DENABLE_MANAGED_USERS=1
> -DENABLE_MDNS=1 -DENABLE_SERVICE_DISCOVERY=1 -DUSE_NSS=1
> -DMEMORY_TOOL_REPLACES_ALLOCATOR -DTHREAD_SANITIZER
> -DDYNAMIC_ANNOTATIONS_EXTERNAL_IMPL=1
> -DWTF_USE_DYNAMIC_ANNOTATIONS_NOIMPL=1 -DNDEBUG
> -DDYNAMIC_ANNOTATIONS_ENABLED=1 -DWTF_USE_DYNAMIC_ANNOTATIONS=1
> -I../../third_party/mesa/src/src/gallium/auxiliary
> -I../../third_party/mesa/src/src/gallium/include
> -I../../third_party/mesa/src/src/glsl
> -I../../third_party/mesa/src/src/glsl/glcpp
> -I../../third_party/mesa/src/src/mapi
> -I../../third_party/mesa/src/src/mapi/glapi
> -I../../third_party/mesa/src/src/mesa
> -I../../third_party/mesa/src/src/mesa/main
> -I../../third_party/mesa/src/chromium_gensrc/mesa
> -I../../third_party/mesa/src/chromium_gensrc/mesa/main
> -I../../third_party/mesa/src/chromium_gensrc/mesa/program
> -I../../third_party/mesa/src/chromium_gensrc/mesa/glapi
> -I../../third_party/mesa/src/include
> '-I../../third_party/libc++/trunk/include'
> '-I../../third_party/libc++abi/trunk/include' -fstack-protector
> --param=ssp-buffer-size=4 -Werror -pthread -fno-exceptions
> -fno-strict-aliasing -Wno-unused-parameter
> -Wno-missing-field-initializers -fvisibility=hidden -pipe -fPIC
> -Wheader-hygiene -Wno-char-subscripts
> -Wno-unneeded-internal-declaration -Wno-covered-switch-default
> -Wno-c++11-narrowing -Wno-reserved-user-defined-literal
> -Wno-deprecated-register -Wno-absolute-value -fcolor-diagnostics
> -B/usr/local/google/home/dtoolsbot/llvm-buildbot/slave/linux-chrome-tsan/build/chrome/src/third_party/binutils/Linux_x64/Release/bin
> -fPIC -Wno-tautological-constant-out-of-range-compare -Wno-format
> -Wno-unused-result -m64 -march=x86-64 -fno-omit-frame-pointer
> -gline-tables-only -fsanitize=thread -fPIC
> -fsanitize-blacklist=../../tools/valgrind/tsan_v2/ignores.txt -O2
> -fdata-sections -ffunction-sections -funwind-tables -c
> ../../third_party/mesa/src/src/mesa/main/pack.c -o
> obj/third_party/mesa/src/src/mesa/main/mesa.pack.o
> clang-3.5: /usr/local/google/home/dtoolsbot/llvm-buildbot/slave/linux-chrome-tsan/build/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp:3066:
> llvm::SDValue llvm::SelectionDAG::getNode(unsigned int, llvm::SDLoc,
> llvm::EVT, llvm::SDValue, llvm::SDValue): Assertion `(!VT.isVector()
> || VT == N2.getValueType()) && "Vector shift amounts must be in the
> same as their first arg"' failed.
> 0 clang-3.5 0x000000000113c372 llvm::sys::PrintStackTrace(_IO_FILE*) + 34
> 1 clang-3.5 0x000000000113bf94
> 2 libpthread.so.0 0x00007f3f46cb2cb0
> 3 libc.so.6 0x00007f3f45eed425 gsignal + 53
> 4 libc.so.6 0x00007f3f45ef0b8b abort + 379
> 5 libc.so.6 0x00007f3f45ee60ee
> 6 libc.so.6 0x00007f3f45ee6192
> 7 clang-3.5 0x0000000001450c87
> llvm::SelectionDAG::getNode(unsigned int, llvm::SDLoc, llvm::EVT,
> llvm::SDValue, llvm::SDValue) + 6983
> 8 clang-3.5 0x000000000154852f
> 9 clang-3.5 0x0000000001550c4b
> 10 clang-3.5 0x00000000014e9806
> 11 clang-3.5 0x00000000014ea19a llvm::SelectionDAG::LegalizeTypes() + 938
> 12 clang-3.5 0x00000000014a798c
> llvm::SelectionDAGISel::CodeGenAndEmitDAG() + 540
> 13 clang-3.5 0x00000000014ac327
> llvm::SelectionDAGISel::SelectAllBasicBlocks(llvm::Function const&) +
> 1719
> 14 clang-3.5 0x00000000014ad740
> llvm::SelectionDAGISel::runOnMachineFunction(llvm::MachineFunction&) +
> 800
> 15 clang-3.5 0x0000000000ebbecf
> llvm::FPPassManager::runOnFunction(llvm::Function&) + 655
> 16 clang-3.5 0x0000000000ebc3ab
> llvm::FPPassManager::runOnModule(llvm::Module&) + 43
> 17 clang-3.5 0x0000000000ebc6ed
> llvm::legacy::PassManagerImpl::run(llvm::Module&) + 797
> 18 clang-3.5 0x000000000175c7be
> clang::EmitBackendOutput(clang::DiagnosticsEngine&,
> clang::CodeGenOptions const&, clang::TargetOptions const&,
> clang::LangOptions const&, llvm::StringRef, llvm::Module*,
> clang::BackendAction, llvm::raw_ostream*) + 2990
> 19 clang-3.5 0x000000000175726f
> 20 clang-3.5 0x0000000001ba7e2b clang::ParseAST(clang::Sema&,
> bool, bool) + 507
> 21 clang-3.5 0x0000000001757e1b clang::CodeGenAction::ExecuteAction() + 59
> 22 clang-3.5 0x0000000001293d26 clang::FrontendAction::Execute() + 150
> 23 clang-3.5 0x00000000012763e0
> clang::CompilerInstance::ExecuteAction(clang::FrontendAction&) + 352
> 24 clang-3.5 0x0000000001310781
> clang::ExecuteCompilerInvocation(clang::CompilerInstance*) + 1921
> 25 clang-3.5 0x00000000006dd3c8 cc1_main(char const**, char
> const**, char const*, void*) + 1272
> 26 clang-3.5 0x00000000006b6c13 main + 755
> 27 libc.so.6 0x00007f3f45ed876d __libc_start_main + 237
> 28 clang-3.5 0x00000000006db0a9
>
> On Mon, May 19, 2014 at 5:12 PM, Benjamin Kramer
> <benny.kra at googlemail.com> wrote:
>> Author: d0k
>> Date: Mon May 19 08:12:38 2014
>> New Revision: 209123
>>
>> URL: http://llvm.org/viewvc/llvm-project?rev=209123&view=rev
>> Log:
>> SDAG: Legalize vector BSWAP into a shuffle if the shuffle is legal but the bswap not.
>>
>> - On ARM/ARM64 we get a vrev because the shuffle matching code is really smart. We still unroll anything that's not v4i32 though.
>> - On X86 we get a pshufb with SSSE3. Required more cleverness in isShuffleMaskLegal.
>> - On PPC we get a vperm for v8i16 and v4i32. v2i64 is unrolled.
>>
>> Modified:
>> llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp
>> llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
>> llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
>> llvm/trunk/lib/Target/ARM64/ARM64ISelLowering.cpp
>> llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp
>> llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
>> llvm/trunk/test/CodeGen/ARM/vrev.ll
>> llvm/trunk/test/CodeGen/ARM64/rev.ll
>> llvm/trunk/test/CodeGen/X86/bswap-vector.ll
>>
>> Modified: llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp (original)
>> +++ llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp Mon May 19 08:12:38 2014
>> @@ -63,6 +63,8 @@ class VectorLegalizer {
>> SDValue ExpandUINT_TO_FLOAT(SDValue Op);
>> // Implement expansion for SIGN_EXTEND_INREG using SRL and SRA.
>> SDValue ExpandSEXTINREG(SDValue Op);
>> + // Expand bswap of vectors into a shuffle if legal.
>> + SDValue ExpandBSWAP(SDValue Op);
>> // Implement vselect in terms of XOR, AND, OR when blend is not supported
>> // by the target.
>> SDValue ExpandVSELECT(SDValue Op);
>> @@ -297,6 +299,8 @@ SDValue VectorLegalizer::LegalizeOp(SDVa
>> case TargetLowering::Expand:
>> if (Node->getOpcode() == ISD::SIGN_EXTEND_INREG)
>> Result = ExpandSEXTINREG(Op);
>> + else if (Node->getOpcode() == ISD::BSWAP)
>> + Result = ExpandBSWAP(Op);
>> else if (Node->getOpcode() == ISD::VSELECT)
>> Result = ExpandVSELECT(Op);
>> else if (Node->getOpcode() == ISD::SELECT)
>> @@ -682,6 +686,29 @@ SDValue VectorLegalizer::ExpandSEXTINREG
>> return DAG.getNode(ISD::SRA, DL, VT, Op, ShiftSz);
>> }
>>
>> +SDValue VectorLegalizer::ExpandBSWAP(SDValue Op) {
>> + EVT VT = Op.getValueType();
>> +
>> + // Generate a byte wise shuffle mask for the BSWAP.
>> + SmallVector<int, 16> ShuffleMask;
>> + int ScalarSizeInBytes = VT.getScalarSizeInBits() / 8;
>> + for (int I = 0, E = VT.getVectorNumElements(); I != E; ++I)
>> + for (int J = ScalarSizeInBytes - 1; J >= 0; --J)
>> + ShuffleMask.push_back((I * ScalarSizeInBytes) + J);
>> +
>> + EVT ByteVT = EVT::getVectorVT(*DAG.getContext(), MVT::i8, ShuffleMask.size());
>> +
>> + // Only emit a shuffle if the mask is legal.
>> + if (!TLI.isShuffleMaskLegal(ShuffleMask, ByteVT))
>> + return DAG.UnrollVectorOp(Op.getNode());
>> +
>> + SDLoc DL(Op);
>> + Op = DAG.getNode(ISD::BITCAST, DL, ByteVT, Op.getOperand(0));
>> + Op = DAG.getVectorShuffle(ByteVT, DL, Op, DAG.getUNDEF(ByteVT),
>> + ShuffleMask.data());
>> + return DAG.getNode(ISD::BITCAST, DL, VT, Op);
>> +}
>> +
>> SDValue VectorLegalizer::ExpandVSELECT(SDValue Op) {
>> // Implement VSELECT in terms of XOR, AND, OR
>> // on platforms which do not support blend natively.
>>
>> Modified: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp (original)
>> +++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp Mon May 19 08:12:38 2014
>> @@ -520,6 +520,8 @@ AArch64TargetLowering::AArch64TargetLowe
>> setOperationAction(ISD::SMUL_LOHI, VT, Expand);
>> setOperationAction(ISD::MULHU, VT, Expand);
>> setOperationAction(ISD::UMUL_LOHI, VT, Expand);
>> +
>> + setOperationAction(ISD::BSWAP, VT, Expand);
>> }
>>
>> // There is no v1i64/v2i64 multiply, expand v1i64/v2i64 to GPR i64 multiply.
>>
>> Modified: llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp (original)
>> +++ llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp Mon May 19 08:12:38 2014
>> @@ -414,6 +414,8 @@ ARMTargetLowering::ARMTargetLowering(Tar
>> setOperationAction(ISD::SMUL_LOHI, (MVT::SimpleValueType)VT, Expand);
>> setOperationAction(ISD::MULHU, (MVT::SimpleValueType)VT, Expand);
>> setOperationAction(ISD::UMUL_LOHI, (MVT::SimpleValueType)VT, Expand);
>> +
>> + setOperationAction(ISD::BSWAP, (MVT::SimpleValueType)VT, Expand);
>> }
>>
>> setOperationAction(ISD::ConstantFP, MVT::f32, Custom);
>>
>> Modified: llvm/trunk/lib/Target/ARM64/ARM64ISelLowering.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM64/ARM64ISelLowering.cpp?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/Target/ARM64/ARM64ISelLowering.cpp (original)
>> +++ llvm/trunk/lib/Target/ARM64/ARM64ISelLowering.cpp Mon May 19 08:12:38 2014
>> @@ -450,6 +450,8 @@ ARM64TargetLowering::ARM64TargetLowering
>> setOperationAction(ISD::MULHU, (MVT::SimpleValueType)VT, Expand);
>> setOperationAction(ISD::UMUL_LOHI, (MVT::SimpleValueType)VT, Expand);
>>
>> + setOperationAction(ISD::BSWAP, (MVT::SimpleValueType)VT, Expand);
>> +
>> for (unsigned InnerVT = (unsigned)MVT::FIRST_VECTOR_VALUETYPE;
>> InnerVT <= (unsigned)MVT::LAST_VECTOR_VALUETYPE; ++InnerVT)
>> setTruncStoreAction((MVT::SimpleValueType)VT,
>>
>> Modified: llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp (original)
>> +++ llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp Mon May 19 08:12:38 2014
>> @@ -460,6 +460,7 @@ PPCTargetLowering::PPCTargetLowering(PPC
>> setOperationAction(ISD::SDIVREM, VT, Expand);
>> setOperationAction(ISD::SCALAR_TO_VECTOR, VT, Expand);
>> setOperationAction(ISD::FPOW, VT, Expand);
>> + setOperationAction(ISD::BSWAP, VT, Expand);
>> setOperationAction(ISD::CTPOP, VT, Expand);
>> setOperationAction(ISD::CTLZ, VT, Expand);
>> setOperationAction(ISD::CTLZ_ZERO_UNDEF, VT, Expand);
>>
>> Modified: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelLowering.cpp?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp (original)
>> +++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp Mon May 19 08:12:38 2014
>> @@ -15116,7 +15116,23 @@ X86TargetLowering::isShuffleMaskLegal(co
>> if (VT.getSizeInBits() == 64)
>> return false;
>>
>> - // FIXME: pshufb, blends, shifts.
>> + // If this is a single-input shuffle with no 128 bit lane crossings we can
>> + // lower it into pshufb.
>> + if ((SVT.is128BitVector() && Subtarget->hasSSSE3()) ||
>> + (SVT.is256BitVector() && Subtarget->hasInt256())) {
>> + bool isLegal = true;
>> + for (unsigned I = 0, E = M.size(); I != E; ++I) {
>> + if (M[I] >= (int)SVT.getVectorNumElements() ||
>> + ShuffleCrosses128bitLane(SVT, I, M[I])) {
>> + isLegal = false;
>> + break;
>> + }
>> + }
>> + if (isLegal)
>> + return true;
>> + }
>> +
>> + // FIXME: blends, shifts.
>> return (SVT.getVectorNumElements() == 2 ||
>> ShuffleVectorSDNode::isSplatMask(&M[0], VT) ||
>> isMOVLMask(M, SVT) ||
>>
>> Modified: llvm/trunk/test/CodeGen/ARM/vrev.ll
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/ARM/vrev.ll?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/ARM/vrev.ll (original)
>> +++ llvm/trunk/test/CodeGen/ARM/vrev.ll Mon May 19 08:12:38 2014
>> @@ -178,3 +178,11 @@ entry:
>> ret void
>> }
>>
>> +define <4 x i32> @test_vrev32_bswap(<4 x i32> %source) nounwind {
>> +; CHECK-LABEL: test_vrev32_bswap:
>> +; CHECK: vrev32.8
>> + %bswap = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %source)
>> + ret <4 x i32> %bswap
>> +}
>> +
>> +declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>) nounwind readnone
>>
>> Modified: llvm/trunk/test/CodeGen/ARM64/rev.ll
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/ARM64/rev.ll?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/ARM64/rev.ll (original)
>> +++ llvm/trunk/test/CodeGen/ARM64/rev.ll Mon May 19 08:12:38 2014
>> @@ -222,3 +222,14 @@ entry:
>> ret void
>> }
>>
>> +
>> +define <4 x i32> @test_vrev32_bswap(<4 x i32> %source) nounwind {
>> +; CHECK-LABEL: test_vrev32_bswap:
>> +; CHECK: rev32.16b
>> +; CHECK-NOT: rev
>> +; CHECK: ret
>> + %bswap = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %source)
>> + ret <4 x i32> %bswap
>> +}
>> +
>> +declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>) nounwind readnone
>>
>> Modified: llvm/trunk/test/CodeGen/X86/bswap-vector.ll
>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/bswap-vector.ll?rev=209123&r1=209122&r2=209123&view=diff
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/X86/bswap-vector.ll (original)
>> +++ llvm/trunk/test/CodeGen/X86/bswap-vector.ll Mon May 19 08:12:38 2014
>> @@ -1,19 +1,127 @@
>> -; RUN: llc < %s -mcpu=x86_64 | FileCheck %s
>> +; RUN: llc < %s -mcpu=x86-64 | FileCheck %s -check-prefix=CHECK-NOSSSE3
>> +; RUN: llc < %s -mcpu=core2 | FileCheck %s -check-prefix=CHECK-SSSE3
>> +; RUN: llc < %s -mcpu=core-avx2 | FileCheck %s -check-prefix=CHECK-AVX2
>> target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
>> target triple = "x86_64-unknown-linux-gnu"
>>
>> +declare <8 x i16> @llvm.bswap.v8i16(<8 x i16>)
>> +declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>)
>> declare <2 x i64> @llvm.bswap.v2i64(<2 x i64>)
>>
>> -define <2 x i64> @foo(<2 x i64> %v) #0 {
>> +define <8 x i16> @test1(<8 x i16> %v) #0 {
>> +entry:
>> + %r = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %v)
>> + ret <8 x i16> %r
>> +
>> +; CHECK-NOSSSE3-LABEL: @test1
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: rolw
>> +; CHECK-NOSSSE3: retq
>> +
>> +; CHECK-SSSE3-LABEL: @test1
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3-NEXT: retq
>> +
>> +; CHECK-AVX2-LABEL: @test1
>> +; CHECK-AVX2: vpshufb
>> +; CHECK-AVX2-NEXT: retq
>> +}
>> +
>> +define <4 x i32> @test2(<4 x i32> %v) #0 {
>> +entry:
>> + %r = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %v)
>> + ret <4 x i32> %r
>> +
>> +; CHECK-NOSSSE3-LABEL: @test2
>> +; CHECK-NOSSSE3: bswapl
>> +; CHECK-NOSSSE3: bswapl
>> +; CHECK-NOSSSE3: bswapl
>> +; CHECK-NOSSSE3: bswapl
>> +; CHECK-NOSSSE3: retq
>> +
>> +; CHECK-SSSE3-LABEL: @test2
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3-NEXT: retq
>> +
>> +; CHECK-AVX2-LABEL: @test2
>> +; CHECK-AVX2: vpshufb
>> +; CHECK-AVX2-NEXT: retq
>> +}
>> +
>> +define <2 x i64> @test3(<2 x i64> %v) #0 {
>> entry:
>> %r = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> %v)
>> ret <2 x i64> %r
>> +
>> +; CHECK-NOSSSE3-LABEL: @test3
>> +; CHECK-NOSSSE3: bswapq
>> +; CHECK-NOSSSE3: bswapq
>> +; CHECK-NOSSSE3: retq
>> +
>> +; CHECK-SSSE3-LABEL: @test3
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3-NEXT: retq
>> +
>> +; CHECK-AVX2-LABEL: @test3
>> +; CHECK-AVX2: vpshufb
>> +; CHECK-AVX2-NEXT: retq
>> +}
>> +
>> +declare <16 x i16> @llvm.bswap.v16i16(<16 x i16>)
>> +declare <8 x i32> @llvm.bswap.v8i32(<8 x i32>)
>> +declare <4 x i64> @llvm.bswap.v4i64(<4 x i64>)
>> +
>> +define <16 x i16> @test4(<16 x i16> %v) #0 {
>> +entry:
>> + %r = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> %v)
>> + ret <16 x i16> %r
>> +
>> +; CHECK-SSSE3-LABEL: @test4
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3-NEXT: retq
>> +
>> +; CHECK-AVX2-LABEL: @test4
>> +; CHECK-AVX2: vpshufb
>> +; CHECK-AVX2-NEXT: retq
>> +}
>> +
>> +define <8 x i32> @test5(<8 x i32> %v) #0 {
>> +entry:
>> + %r = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> %v)
>> + ret <8 x i32> %r
>> +
>> +; CHECK-SSSE3-LABEL: @test5
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3-NEXT: retq
>> +
>> +; CHECK-AVX2-LABEL: @test5
>> +; CHECK-AVX2: vpshufb
>> +; CHECK-AVX2-NEXT: retq
>> +}
>> +
>> +define <4 x i64> @test6(<4 x i64> %v) #0 {
>> +entry:
>> + %r = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> %v)
>> + ret <4 x i64> %r
>> +
>> +; CHECK-SSSE3-LABEL: @test6
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3: pshufb
>> +; CHECK-SSSE3-NEXT: retq
>> +
>> +; CHECK-AVX2-LABEL: @test6
>> +; CHECK-AVX2: vpshufb
>> +; CHECK-AVX2-NEXT: retq
>> }
>>
>> -; CHECK-LABEL: @foo
>> -; CHECK: bswapq
>> -; CHECK: bswapq
>> -; CHECK: retq
>>
>> attributes #0 = { nounwind uwtable }
>>
>>
>>
>> _______________________________________________
>> llvm-commits mailing list
>> llvm-commits at cs.uiuc.edu
>> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
>
>
>
> --
> Alexander Potapenko
> Software Engineer
> Google Moscow
More information about the llvm-commits
mailing list