forked from OSchip/llvm-project
67e4330fac
Summary: The following intrinsics have been extended to support brain float types: svbfloat16_t svclasta[_bf16](svbool_t pg, svbfloat16_t fallback, svbfloat16_t data) bfloat16_t svclasta[_n_bf16](svbool_t pg, bfloat16_t fallback, svbfloat16_t data) bfloat16_t svlasta[_bf16](svbool_t pg, svbfloat16_t op) svbfloat16_t svclastb[_bf16](svbool_t pg, svbfloat16_t fallback, svbfloat16_t data) bfloat16_t svclastb[_n_bf16](svbool_t pg, bfloat16_t fallback, svbfloat16_t data) bfloat16_t svlastb[_bf16](svbool_t pg, svbfloat16_t op) svbfloat16_t svdup[_n]_bf16(bfloat16_t op) svbfloat16_t svdup[_n]_bf16_m(svbfloat16_t inactive, svbool_t pg, bfloat16_t op) svbfloat16_t svdup[_n]_bf16_x(svbool_t pg, bfloat16_t op) svbfloat16_t svdup[_n]_bf16_z(svbool_t pg, bfloat16_t op) svbfloat16_t svdupq[_n]_bf16(bfloat16_t x0, bfloat16_t x1, bfloat16_t x2, bfloat16_t x3, bfloat16_t x4, bfloat16_t x5, bfloat16_t x6, bfloat16_t x7) svbfloat16_t svdupq_lane[_bf16](svbfloat16_t data, uint64_t index) svbfloat16_t svinsr[_n_bf16](svbfloat16_t op1, bfloat16_t op2) Reviewers: sdesmalen, kmclaughlin, c-rhodes, ctetreau, efriedma Subscribers: tschuett, hiraditya, rkruppe, psnobl, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D82345 |
||
---|---|---|
.. | ||
ABIInfo.h | ||
Address.h | ||
BackendUtil.cpp | ||
CGAtomic.cpp | ||
CGBlocks.cpp | ||
CGBlocks.h | ||
CGBuilder.h | ||
CGBuiltin.cpp | ||
CGCUDANV.cpp | ||
CGCUDARuntime.cpp | ||
CGCUDARuntime.h | ||
CGCXX.cpp | ||
CGCXXABI.cpp | ||
CGCXXABI.h | ||
CGCall.cpp | ||
CGCall.h | ||
CGClass.cpp | ||
CGCleanup.cpp | ||
CGCleanup.h | ||
CGCoroutine.cpp | ||
CGDebugInfo.cpp | ||
CGDebugInfo.h | ||
CGDecl.cpp | ||
CGDeclCXX.cpp | ||
CGException.cpp | ||
CGExpr.cpp | ||
CGExprAgg.cpp | ||
CGExprCXX.cpp | ||
CGExprComplex.cpp | ||
CGExprConstant.cpp | ||
CGExprScalar.cpp | ||
CGGPUBuiltin.cpp | ||
CGLoopInfo.cpp | ||
CGLoopInfo.h | ||
CGNonTrivialStruct.cpp | ||
CGObjC.cpp | ||
CGObjCGNU.cpp | ||
CGObjCMac.cpp | ||
CGObjCRuntime.cpp | ||
CGObjCRuntime.h | ||
CGOpenCLRuntime.cpp | ||
CGOpenCLRuntime.h | ||
CGOpenMPRuntime.cpp | ||
CGOpenMPRuntime.h | ||
CGOpenMPRuntimeNVPTX.cpp | ||
CGOpenMPRuntimeNVPTX.h | ||
CGRecordLayout.h | ||
CGRecordLayoutBuilder.cpp | ||
CGStmt.cpp | ||
CGStmtOpenMP.cpp | ||
CGVTT.cpp | ||
CGVTables.cpp | ||
CGVTables.h | ||
CGValue.h | ||
CMakeLists.txt | ||
CodeGenABITypes.cpp | ||
CodeGenAction.cpp | ||
CodeGenFunction.cpp | ||
CodeGenFunction.h | ||
CodeGenModule.cpp | ||
CodeGenModule.h | ||
CodeGenPGO.cpp | ||
CodeGenPGO.h | ||
CodeGenTBAA.cpp | ||
CodeGenTBAA.h | ||
CodeGenTypeCache.h | ||
CodeGenTypes.cpp | ||
CodeGenTypes.h | ||
ConstantEmitter.h | ||
ConstantInitBuilder.cpp | ||
CoverageMappingGen.cpp | ||
CoverageMappingGen.h | ||
EHScopeStack.h | ||
ItaniumCXXABI.cpp | ||
MacroPPCallbacks.cpp | ||
MacroPPCallbacks.h | ||
MicrosoftCXXABI.cpp | ||
ModuleBuilder.cpp | ||
ObjectFilePCHContainerOperations.cpp | ||
PatternInit.cpp | ||
PatternInit.h | ||
README.txt | ||
SanitizerMetadata.cpp | ||
SanitizerMetadata.h | ||
SwiftCallingConv.cpp | ||
TargetInfo.cpp | ||
TargetInfo.h | ||
VarBypassDetector.cpp | ||
VarBypassDetector.h |
README.txt
IRgen optimization opportunities. //===---------------------------------------------------------------------===// The common pattern of -- short x; // or char, etc (x == 10) -- generates an zext/sext of x which can easily be avoided. //===---------------------------------------------------------------------===// Bitfields accesses can be shifted to simplify masking and sign extension. For example, if the bitfield width is 8 and it is appropriately aligned then is is a lot shorter to just load the char directly. //===---------------------------------------------------------------------===// It may be worth avoiding creation of alloca's for formal arguments for the common situation where the argument is never written to or has its address taken. The idea would be to begin generating code by using the argument directly and if its address is taken or it is stored to then generate the alloca and patch up the existing code. In theory, the same optimization could be a win for block local variables as long as the declaration dominates all statements in the block. NOTE: The main case we care about this for is for -O0 -g compile time performance, and in that scenario we will need to emit the alloca anyway currently to emit proper debug info. So this is blocked by being able to emit debug information which refers to an LLVM temporary, not an alloca. //===---------------------------------------------------------------------===// We should try and avoid generating basic blocks which only contain jumps. At -O0, this penalizes us all the way from IRgen (malloc & instruction overhead), all the way down through code generation and assembly time. On 176.gcc:expr.ll, it looks like over 12% of basic blocks are just direct branches! //===---------------------------------------------------------------------===//