<feed xmlns='http://www.w3.org/2005/Atom'>
<title>llvm-project.git/llvm/test/CodeGen/SPIRV/pointers/getelementptr-bitcast-load.ll, branch users/nico/python-2</title>
<subtitle>Unnamed repository; edit this file 'description' to name the repository.
</subtitle>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/'/>
<entry>
<title>[SPIR-V] Rework usage of virtual registers' types and classes (#104104)</title>
<updated>2024-08-22T07:40:27+00:00</updated>
<author>
<name>Vyacheslav Levytskyy</name>
<email>vyacheslav.levytskyy@intel.com</email>
</author>
<published>2024-08-22T07:40:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=67d3ef74b31e1517d4f679e754cc2b3041c95901'/>
<id>67d3ef74b31e1517d4f679e754cc2b3041c95901</id>
<content type='text'>
This PR continues https://github.com/llvm/llvm-project/pull/101732
changes in virtual register processing aimed to improve correctness of
emitted MIR between passes from the perspective of MachineVerifier.
Namely, the following changes are introduced:
* register classes (lib/Target/SPIRV/SPIRVRegisterInfo.td) and
instruction patterns (lib/Target/SPIRV/SPIRVInstrInfo.td) are corrected
and simplified (by removing unnecessary sophisticated options) -- e.g.,
this PR gets rid of duplicating 32/64 bits patterns, removes ANYID
register class and simplifies definition of the rest of register
classes,
* hardcoded LLT scalar types in passes before instruction selection are
corrected -- the goal is to have correct bit width before instruction
selection, and use 64 bits registers for pattern matching in the
instruction selection pass; 32-bit registers remain where they are
described in such terms by SPIR-V specification (like, for example,
creation of virtual registers for scope/mem semantics operands),
* rework virtual register type/class assignment for calls/builtins
lowering,
* a series of minor changes to fix validity of emitted code between
passes:
  - ensure that that bitcast changes the type,
  - fix the pattern for instruction selection for OpExtInst,
  - simplify inline asm operands usage,
  - account for arbitrary integer sizes / update legalizer rules;
* add '-verify-machineinstrs' to existed test cases.

See also https://github.com/llvm/llvm-project/issues/88129 that this PR
may resolve.

This PR fixes a great number of issues reported by MachineVerifier and,
as a result, reduces a number of failed test cases for the mode with
expensive checks set on from ~200 to ~57.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This PR continues https://github.com/llvm/llvm-project/pull/101732
changes in virtual register processing aimed to improve correctness of
emitted MIR between passes from the perspective of MachineVerifier.
Namely, the following changes are introduced:
* register classes (lib/Target/SPIRV/SPIRVRegisterInfo.td) and
instruction patterns (lib/Target/SPIRV/SPIRVInstrInfo.td) are corrected
and simplified (by removing unnecessary sophisticated options) -- e.g.,
this PR gets rid of duplicating 32/64 bits patterns, removes ANYID
register class and simplifies definition of the rest of register
classes,
* hardcoded LLT scalar types in passes before instruction selection are
corrected -- the goal is to have correct bit width before instruction
selection, and use 64 bits registers for pattern matching in the
instruction selection pass; 32-bit registers remain where they are
described in such terms by SPIR-V specification (like, for example,
creation of virtual registers for scope/mem semantics operands),
* rework virtual register type/class assignment for calls/builtins
lowering,
* a series of minor changes to fix validity of emitted code between
passes:
  - ensure that that bitcast changes the type,
  - fix the pattern for instruction selection for OpExtInst,
  - simplify inline asm operands usage,
  - account for arbitrary integer sizes / update legalizer rules;
* add '-verify-machineinstrs' to existed test cases.

See also https://github.com/llvm/llvm-project/issues/88129 that this PR
may resolve.

This PR fixes a great number of issues reported by MachineVerifier and,
as a result, reduces a number of failed test cases for the mode with
expensive checks set on from ~200 to ~57.</pre>
</div>
</content>
</entry>
<entry>
<title>[SPIR-V] Do not emit spv_ptrcast if GEP result is of expected type (#78122)</title>
<updated>2024-01-16T03:56:11+00:00</updated>
<author>
<name>Michal Paszkowski</name>
<email>michal@paszkowski.org</email>
</author>
<published>2024-01-16T03:56:11+00:00</published>
<link rel='alternate' type='text/html' href='https://git.belthelziquor.com/llvm-project.git/commit/?id=59e5cb7b83fbbce2423e0c024861f83c0390670f'/>
<id>59e5cb7b83fbbce2423e0c024861f83c0390670f</id>
<content type='text'>
Prior to this change spv_ptrcast (and OpBitcast) was never emitted for
GEP resulting pointers. While such SPIR-V was (mostly) accepted by the
NEO GPU driver, the generated SPIR-V was incorrect.

The newly added test (pointers/getelementptr-bitcast-load.ll) verifies
that a correct bitcast is added for more complex cases and passes
spirv-val. The test is based on an OpenCL CTS test (basic/prefetch).</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Prior to this change spv_ptrcast (and OpBitcast) was never emitted for
GEP resulting pointers. While such SPIR-V was (mostly) accepted by the
NEO GPU driver, the generated SPIR-V was incorrect.

The newly added test (pointers/getelementptr-bitcast-load.ll) verifies
that a correct bitcast is added for more complex cases and passes
spirv-val. The test is based on an OpenCL CTS test (basic/prefetch).</pre>
</div>
</content>
</entry>
</feed>
