mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 03:33:20 +01:00
5f36b4cd05
Summary:
According to PTX ISA:
For convenience, ld, st, and cvt instructions permit source and destination data operands to be wider than the instruction-type size, so that narrow values may be loaded, stored, and converted using regular-width registers. For example, 8-bit or 16-bit values may be held directly in 32-bit or 64-bit registers when being loaded, stored, or converted to other types and sizes. The operand type checking rules are relaxed for bit-size and integer (signed and unsigned) instruction types; floating-point instruction types still require that the operand type-size matches exactly, unless the operand is of bit-size type.
So, the ISA does not support load with extending/store with truncatation for floating numbers. This is reflected in setting the loadext/truncstore actions to expand in the code for floating numbers, but vectors of floating numbers are not taken care of.
As a result, loading a vector of floats followed by a fp_extend may be combined by DAGCombiner to a extload, and the extload may be lowered to NVPTXISD::LoadV2 with extending information. However, NVPTXISD::LoadV2 does not perform extending, and no extending instructions are inserted. Finally, PTX instructions with mismatched types are generated, like
ld.v2.f32 {%fd3, %fd4}, [%rd2]
This patch adds the correct actions for vectors of floats, so DAGCombiner would not create loads with extending, and correct code is generated.
Patched by Gang Hu.
Test Plan: Test case attached.
Reviewers: jingyue
Reviewed By: jingyue
Subscribers: llvm-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D10876
llvm-svn: 241191
|
||
|---|---|---|
| .. | ||
| InstPrinter | ||
| MCTargetDesc | ||
| TargetInfo | ||
| cl_common_defines.h | ||
| CMakeLists.txt | ||
| LLVMBuild.txt | ||
| Makefile | ||
| ManagedStringPool.h | ||
| NVPTX.h | ||
| NVPTX.td | ||
| NVPTXAllocaHoisting.cpp | ||
| NVPTXAllocaHoisting.h | ||
| NVPTXAsmPrinter.cpp | ||
| NVPTXAsmPrinter.h | ||
| NVPTXAssignValidGlobalNames.cpp | ||
| NVPTXFavorNonGenericAddrSpaces.cpp | ||
| NVPTXFrameLowering.cpp | ||
| NVPTXFrameLowering.h | ||
| NVPTXGenericToNVVM.cpp | ||
| NVPTXImageOptimizer.cpp | ||
| NVPTXInstrFormats.td | ||
| NVPTXInstrInfo.cpp | ||
| NVPTXInstrInfo.h | ||
| NVPTXInstrInfo.td | ||
| NVPTXIntrinsics.td | ||
| NVPTXISelDAGToDAG.cpp | ||
| NVPTXISelDAGToDAG.h | ||
| NVPTXISelLowering.cpp | ||
| NVPTXISelLowering.h | ||
| NVPTXLowerAggrCopies.cpp | ||
| NVPTXLowerAggrCopies.h | ||
| NVPTXLowerAlloca.cpp | ||
| NVPTXLowerKernelArgs.cpp | ||
| NVPTXMachineFunctionInfo.h | ||
| NVPTXMCExpr.cpp | ||
| NVPTXMCExpr.h | ||
| NVPTXPeephole.cpp | ||
| NVPTXPrologEpilogPass.cpp | ||
| NVPTXRegisterInfo.cpp | ||
| NVPTXRegisterInfo.h | ||
| NVPTXRegisterInfo.td | ||
| NVPTXReplaceImageHandles.cpp | ||
| NVPTXSection.h | ||
| NVPTXSubtarget.cpp | ||
| NVPTXSubtarget.h | ||
| NVPTXTargetMachine.cpp | ||
| NVPTXTargetMachine.h | ||
| NVPTXTargetObjectFile.h | ||
| NVPTXTargetTransformInfo.cpp | ||
| NVPTXTargetTransformInfo.h | ||
| NVPTXUtilities.cpp | ||
| NVPTXUtilities.h | ||
| NVPTXVector.td | ||
| NVVMReflect.cpp | ||