SuccessChanges

Changes from Git (git http://labmaster3.local/git/llvm-project.git)

Summary

  1. AMDGPU/GlobalISel: Select DS append/consume (details)
  2. AMDGPU/GlobalISel: Select llvm.amdgcn.update.dpp (details)
  3. Consolidate internal denormal flushing controls (details)
  4. TableGen/GlobalISel: Don't check exact intrinsic opcode value (details)
  5. [MLIR] LLVM dialect: modernize and cleanups (details)
Commit ec9628318d797bfe036aca314d58665dd93b364f by arsenm2
AMDGPU/GlobalISel: Select DS append/consume
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.consume.ll
The file was addedllvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.ds.append.ll
The file was modifiedllvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
The file was modifiedllvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
The file was modifiedllvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.append.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.ds.append.mir
The file was modifiedllvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
The file was addedllvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.ds.consume.ll
The file was modifiedllvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.ds.consume.mir
Commit 592de0009f6482fbf033ef87d147aab13fcce78c by arsenm2
AMDGPU/GlobalISel: Select llvm.amdgcn.update.dpp
The existing test is overly reliant on -mattr=-flat-for-global, and some
missing optimizations to re-use.
The file was modifiedllvm/lib/Target/AMDGPU/SIInstructions.td
The file was modifiedllvm/lib/Target/AMDGPU/SIInstrInfo.td
The file was modifiedllvm/lib/Target/AMDGPU/VOP1Instructions.td
The file was modifiedllvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
The file was addedllvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.update.dpp.ll
The file was modifiedllvm/lib/Target/AMDGPU/AMDGPUGISel.td
The file was modifiedllvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
Commit a4451d88ee456304c26d552749aea6a7f5154bde by arsenm2
Consolidate internal denormal flushing controls
Currently there are 4 different mechanisms for controlling denormal
flushing behavior, and about as many equivalent frontend controls.
- AMDGPU uses the fp32-denormals and fp64-f16-denormals subtarget
features
- NVPTX uses the nvptx-f32ftz attribute
- ARM directly uses the denormal-fp-math attribute
- Other targets indirectly use denormal-fp-math in one DAGCombine
- cl-denorms-are-zero has a corresponding denorms-are-zero attribute
AMDGPU wants a distinct control for f32 flushing from f16/f64, and as
far as I can tell the same is true for NVPTX (based on the attribute
name).
Work on consolidating these into the denormal-fp-math attribute, and a
new type specific denormal-fp-math-f32 variant. Only ARM seems to
support the two different flush modes, so this is overkill for the other
use cases. Ideally we would error on the unsupported positive-zero mode
on other targets from somewhere.
Move the logic for selecting the flush mode into the compiler driver,
instead of handling it in cc1. denormal-fp-math/denormal-fp-math-f32 are
now both cc1 flags, but denormal-fp-math-f32 is not yet exposed as a
user flag.
-cl-denorms-are-zero, -fcuda-flush-denormals-to-zero and
-fno-cuda-flush-denormals-to-zero will be mapped to
-fp-denormal-math-f32=ieee or preserve-sign rather than the old
attributes.
Stop emitting the denorms-are-zero attribute for the OpenCL flag. It has
no in-tree users. The meaning would also be target dependent, such as
the AMDGPU choice to treat this as only meaning allow flushing of f32
and not f16 or f64. The naming is also potentially confusing, since DAZ
in other contexts refers to instructions implicitly treating input
denormals as zero, not necessarily flushing output denormals to zero.
This also does not attempt to change the behavior for the current
attribute. The LangRef now states that the default is ieee behavior, but
this is inaccurate for the current implementation. The clang handling is
slightly hacky to avoid touching the existing denormal-fp-math uses.
Fixing this will be left for a future patch.
AMDGPU is still using the subtarget feature to control the denormal
mode, but the new attribute are now emitted. A future change will switch
this and remove the subtarget features.
The file was modifiedclang/lib/CodeGen/CodeGenModule.cpp
The file was removedclang/test/CodeGenOpenCL/denorms-are-zero.cl
The file was modifiedllvm/docs/LangRef.rst
The file was addedclang/test/Driver/cuda-flush-denormals-to-zero.cu
The file was modifiedclang/lib/Basic/Targets/AMDGPU.cpp
The file was modifiedclang/lib/CodeGen/CGCall.cpp
The file was modifiedllvm/test/CodeGen/NVPTX/sqrt-approx.ll
The file was modifiedllvm/test/CodeGen/NVPTX/fast-math.ll
The file was modifiedllvm/test/Transforms/InstCombine/NVPTX/nvvm-intrins.ll
The file was modifiedclang/lib/Driver/ToolChains/Cuda.cpp
The file was modifiedclang/include/clang/Basic/CodeGenOptions.def
The file was addedclang/test/Driver/cl-denorms-are-zero.cl
The file was modifiedclang/lib/Driver/ToolChains/HIP.cpp
The file was modifiedclang/lib/Driver/ToolChains/AMDGPU.h
The file was modifiedclang/test/Driver/denormal-fp-math.c
The file was modifiedclang/test/CodeGenOpenCL/amdgpu-features.cl
The file was modifiedllvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
The file was modifiedclang/test/CodeGenCUDA/flush-denormals.cu
The file was modifiedclang/include/clang/Driver/CC1Options.td
The file was modifiedclang/test/CodeGenCUDA/propagate-metadata.cu
The file was modifiedclang/lib/Driver/ToolChains/AMDGPU.cpp
The file was modifiedclang/test/Driver/opencl.cl
The file was modifiedclang/lib/Driver/ToolChains/Cuda.h
The file was modifiedllvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
The file was modifiedclang/lib/Driver/ToolChains/Clang.cpp
The file was modifiedllvm/lib/CodeGen/MachineFunction.cpp
The file was modifiedclang/include/clang/Basic/CodeGenOptions.h
The file was modifiedclang/include/clang/Driver/ToolChain.h
The file was removedclang/test/CodeGenOpenCL/gfx9-fp32-denorms.cl
The file was modifiedclang/include/clang/Driver/Options.td
The file was modifiedllvm/test/CodeGen/NVPTX/math-intrins.ll
The file was modifiedclang/lib/Frontend/CompilerInvocation.cpp
Commit df7900e2182467fe11637c657d7d9fa9d9b61f48 by arsenm2
TableGen/GlobalISel: Don't check exact intrinsic opcode value
The file was modifiedllvm/test/TableGen/GlobalISelEmitter-input-discard.td
Commit ee2de95507a1fc81069c9b521be891abfe1379fb by frank.laub
[MLIR] LLVM dialect: modernize and cleanups
Summary: Modernize some of the existing custom parsing code in the LLVM
dialect. While this reduces some boilerplate code, it also reduces the
precision of the diagnostic error messges.
Reviewers: ftynse, nicolasvasilache, rriddle
Reviewed By: rriddle
Subscribers: merge_guards_bot, mehdi_amini, rriddle, jpienaar, burmako,
shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, liufengdb,
llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D72967
The file was modifiedmlir/lib/Dialect/LLVMIR/IR/LLVMDialect.cpp
The file was modifiedmlir/test/Dialect/LLVMIR/invalid.mlir