Commit Graph

25 Commits

Author SHA1 Message Date
Tom Stellard 000c5af3e6 AMDGPU: Add skeleton GlobalIsel implementation
Summary:
This adds the necessary target code to be able to run the ir translator.
Lowering function arguments and returns is a nop and there is no support
for RegBankSelect.

Reviewers: arsenm, qcolombet

Subscribers: arsenm, joker.eph, vkalintiris, llvm-commits

Differential Revision: http://reviews.llvm.org/D19077

llvm-svn: 266356
2016-04-14 19:09:28 +00:00
Nicolai Haehnle 723b73b4eb AMDGPU: Remove SIFixSGPRLiveRanges pass
Summary:
This pass is unnecessary and overly conservative. It was motivated by
situations like

  def %vreg0:SGPR_32
  ...
if-block:
  ..
  def %vreg1:SGPR_32
  ...
else-block:
  ...
  use %vreg0:SGPR_32
  ...

and similar situations with uses after the non-uniform control flow, where
we are not allowed to assign %vreg0 and %vreg1 to the same physical register,
even though in the original, thread/workitem-based CFG, it looks like the
live ranges of these registers do not overlap.

However, by the time register allocation runs, we have moved to a wave-based
CFG that accurately represents the fact that the wave may run through both
the if- and the else-block. So the live ranges of %vreg0 and %vreg1 already
overlap even without the SIFixSGPRLiveRanges pass.

In addition to proving this change correct, I have tested it with Piglit
and a small number of other tests.

Reviewers: arsenm, tstellarAMD

Subscribers: MatzeB, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D19041

llvm-svn: 266345
2016-04-14 17:42:29 +00:00
Nicolai Haehnle 213e87f2ee AMDGPU: Add SIWholeQuadMode pass
Summary:
Whole quad mode is already enabled for pixel shaders that compute
derivatives, but it must be suspended for instructions that cause a
shader to have side effects (i.e. stores and atomics).

This pass addresses the issue by storing the real (initial) live mask
in a register, masking EXEC before instructions that require exact
execution and (re-)enabling WQM where required.

This pass is run before register coalescing so that we can use
machine SSA for analysis.

The changes in this patch expose a problem with the second machine
scheduling pass: target independent instructions like COPY implicitly
use EXEC when they operate on VGPRs, but this fact is not encoded in
the MIR. This can lead to miscompilation because instructions are
moved past changes to EXEC.

This patch fixes the problem by adding use-implicit operands to
target independent instructions. Some general codegen passes are
relaxed to work with such implicit use operands.

Reviewers: arsenm, tstellarAMD, mareko

Subscribers: MatzeB, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D18162

llvm-svn: 263982
2016-03-21 20:28:33 +00:00
Tom Stellard cc7067a668 AMDGPU: Insert two S_NOP instructions for every high level source statement.
Patch by: Konstantin Zhuravlyov

Summary: Tools, such as debugger, need to pause execution based on user input (i.e. breakpoint). In order to do this, two S_NOP instructions are inserted for each high level source statement: one before first isa instruction of high level source statement, and one after last isa instruction of high level source statement. Further, debugger may replace S_NOP instructions with S_TRAP instructions based on user input.

Reviewers: tstellarAMD, arsenm

Subscribers: echristo, dblaikie, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D17454

llvm-svn: 262579
2016-03-03 03:53:29 +00:00
Tom Stellard e1818af8c5 [AMDGPU] Disassembler: Added basic disassembler for AMDGPU target
Changes:

- Added disassembler project
- Fixed all decoding conflicts in .td files
- Added DecoderMethod=“NONE” option to Target.td that allows to
  disable decoder generation for an instruction.
- Created decoding functions for VS_32 and VReg_32 register classes.
- Added stubs for decoding all register classes.
- Added several tests for disassembler

Disassembler only supports:

- VI subtarget
- VOP1 instruction encoding
- 32-bit register operands and inline constants

[Valery]

One of the point that requires to pay attention to is how decoder
conflicts were resolved:

- Groups of target instructions were separated by using different
  DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate
  approach.

- There were conflicts in IMAGE_<> instructions caused by two
  different reasons:

1. dmask wasn’t specified for the output (fixed)
2. There are image instructions that differ only by the number of
   the address components but have the same encoding by the HW spec. The
   actual number of address components is determined by the HW at runtime
   using image resource descriptor starting from the VGPR encoded in an
   IMAGE instruction. This means that we should choose only one instruction
   from conflicting group to be the rule for decoder. I didn’t find the way
   to disable decoder generation for an arbitrary instruction and therefore
   made a onelinear fix to tablegen generator that would suppress decoder
   generation when DecoderMethod is set to “NONE”. This is a change that
   should be reviewed and submitted first. Otherwise I would need to
   specify different DecoderNamespace for every instruction in the
   conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not
   used in other targets.
3. IMAGE_GATHER decoder generation is for now disabled and to be
   done later.

[/Valery]

Patch By: Sam Kolton

Differential Revision: http://reviews.llvm.org/D16723

llvm-svn: 261185
2016-02-18 03:42:32 +00:00
Oliver Stannard 7e7d983a87 Refactor backend diagnostics for unsupported features
Re-commit of r258951 after fixing layering violation.

The BPF and WebAssembly backends had identical code for emitting errors
for unsupported features, and AMDGPU had very similar code. This merges
them all into one DiagnosticInfo subclass, that can be used by any
backend.

There should be minimal functional changes here, but some AMDGPU tests
have been updated for the new format of errors (it used a slightly
different format to BPF and WebAssembly). The AMDGPU error messages will
now benefit from having precise source locations when debug info is
available.

llvm-svn: 259498
2016-02-02 13:52:43 +00:00
Oliver Stannard 02fa1c80c4 Revert r259035, it introduces a cyclic library dependency
llvm-svn: 259045
2016-01-28 13:19:47 +00:00
Oliver Stannard b4b092ea1b Add backend dignostic printer for unsupported features
Re-commit of r258951 after fixing layering violation.

The related LLVM patch adds a backend diagnostic type for reporting
unsupported features, this adds a printer for them to clang.

In the case where debug location information is not available, I've
changed the printer to report the location as the first line of the
function, rather than the closing brace, as the latter does not give the
user any information. This also affects optimisation remarks.

Differential Revision: http://reviews.llvm.org/D16590

llvm-svn: 259035
2016-01-28 10:07:27 +00:00
NAKAMURA Takumi 628a7a0aef Revert r258951 (and r258950), "Refactor backend diagnostics for unsupported features"
It broke layering violation in LLVMIR.

clang r258950 "Add backend dignostic printer for unsupported features"
llvm  r258951 "Refactor backend diagnostics for unsupported features"

llvm-svn: 259016
2016-01-28 04:41:32 +00:00
Oliver Stannard 1e67a9f196 Refactor backend diagnostics for unsupported features
The BPF and WebAssembly backends had identical code for emitting errors
for unsupported features, and AMDGPU had very similar code. This merges
them all into one DiagnosticInfo subclass, that can be used by any
backend.

There should be minimal functional changes here, but some AMDGPU tests
have been updated for the new format of errors (it used a slightly
different format to BPF and WebAssembly). The AMDGPU error messages will
now benefit from having precise source locations when debug info is
available.

The implementation of DiagnosticInfoUnsupported::print must be in
lib/Codegen rather than in the existing file in lib/IR/ to avoid
introducing a dependency from IR to CodeGen.

Differential Revision: http://reviews.llvm.org/D16590

llvm-svn: 258951
2016-01-27 17:30:33 +00:00
Nicolai Haehnle 02c3291566 AMDGPU/SI: Add SI Machine Scheduler
Summary:
It is off by default, but can be used
with --misched=si

Patch by: Axel Davy

Reviewers: arsenm, tstellarAMD, nhaehnle

Subscribers: nhaehnle, solenskiner, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D11885

llvm-svn: 257609
2016-01-13 16:10:10 +00:00
Tom Stellard a6f24c6565 AMDGPU/SI: Select constant loads with non-uniform addresses to MUBUF instructions
Summary:
We were previously selecting all constant loads to SMRD instructions and legalizing
the SMRDs with non-uniform addresses during the SIFixSGPRCopesPass.

This new solution is more simple and also generates much better code, because
the instruction selector is able to take advantage of all the MUBUF addressing
modes that are legalization pass wasn't able to.

We also no longer need to generate v_add_* instructions when we
have a uniform pointer and a non-uniform offset, as this is now folded into the
MUBUF instruction during instruction selection.

Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15425

llvm-svn: 255672
2015-12-15 20:55:55 +00:00
Tom Stellard c93fc11f36 AMDGPU/SI: Emit constant arrays in the .text section
Summary:
This allows us to remove the END_OF_TEXT_LABEL hack we had been using
and simplifies the fixups used to compute the address of constant
arrays.

Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15257

llvm-svn: 255204
2015-12-10 02:13:01 +00:00
Matt Arsenault 0e3d38937e AMDGPU: Remove SIPrepareScratchRegs
It does not work because of emergency stack slots.
This pass was supposed to eliminate dummy registers for the
spill instructions, but the register scavenger can introduce
more during PrologEpilogInserter, so some would end up
left behind if they were needed.

The potential for spilling the scratch resource descriptor
and offset register makes doing something like this
overly complicated. Reserve registers to use for the resource
descriptor and use them directly in eliminateFrameIndex.

Also removes creating another scratch resource descriptor
when directly selecting scratch MUBUF instructions.

The choice of which registers are reserved is temporary.
For now it attempts to pick the next available registers
after the user and system SGPRs.

llvm-svn: 254329
2015-11-30 21:15:53 +00:00
Matt Arsenault 0c90e9501e AMDGPU: Create emergency stack slots during frame lowering
Test has a bogus verifier error which will be fixed by later commits.

llvm-svn: 252327
2015-11-06 18:17:45 +00:00
Matt Arsenault 3931948bb6 AMDGPU: Add pass to detect used kernel features
Mark kernels that use certain features that require user
SGPRs to support with kernel attributes. We need to know
before instruction selection begins because it impacts
the kernel calling convention lowering.

For now this only detects the workitem intrinsics.

llvm-svn: 252323
2015-11-06 18:01:57 +00:00
Matt Arsenault b6fd98c7d9 AMDGPU: Split DiagnosticInfoUnsupported into its own file
llvm-svn: 250959
2015-10-21 22:37:46 +00:00
Tom Stellard e135ffd554 AMDGPU/SI: Use .hsatext section instead of .text for HSA
Reviewers: arsenm, grosbach, rafael

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D12424

llvm-svn: 248619
2015-09-25 21:41:28 +00:00
Tom Stellard fd25395c72 AMDGPU: Add pass to lower OpenCL image and sampler arguments.
The pass adds new kernel arguments for image attributes, and
resolves calls to dummy attribute and resource id getter functions.

Patch by: Zoltan Gilian

llvm-svn: 244372
2015-08-07 23:19:30 +00:00
Tom Stellard 347ac79b15 AMDGPU/SI: Add hsa code object directives
Reviewers: arsenm

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D10757

llvm-svn: 240831
2015-06-26 21:15:07 +00:00
Tom Stellard 45bb48ea19 R600 -> AMDGPU rename
llvm-svn: 239657
2015-06-13 03:28:10 +00:00
Tom Stellard 1be1aa84ec Revert "AMDGPU: Add core backend files for R600/SI codegen v6"
This reverts commit 4ea70107c5e51230e9e60f0bf58a0f74aa4885ea.

llvm-svn: 160303
2012-07-16 18:19:53 +00:00
Tom Stellard 1bd3012505 Revert "Target/AMDGPU: [CMake] Fix dependencies. 1) Add intrinsics_gen. Add AMDGPUCommonTableGen."
This reverts commit ebc934ba32ee71abbb8f0f2eb6a0fbaa613ba0d2.

llvm-svn: 160298
2012-07-16 18:19:40 +00:00
NAKAMURA Takumi bb42a5e2cf Target/AMDGPU: [CMake] Fix dependencies. 1) Add intrinsics_gen. Add AMDGPUCommonTableGen.
llvm-svn: 160276
2012-07-16 15:09:11 +00:00
Tom Stellard bcce80fa95 AMDGPU: Add core backend files for R600/SI codegen v6
llvm-svn: 160270
2012-07-16 14:17:08 +00:00