llvm-project.git/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp, branch users/nico/python-2

[Target] Use range-based for loops (NFC) (#146198)

2025-06-28T05:07:58+00:00

AMDGPU: Directly check if shrink-instructions run is post-RA (#142009)

2025-05-30T13:52:18+00:00

[NFC][CodeGen] Adopt MachineFunctionProperties convenience accessors (#141101)

2025-05-23T15:30:29+00:00

Revert "[AMDGPU] remove move instruction if there is no user of it (#136735)"

2025-05-21T03:12:09+00:00

This reverts commit 883afa4ef93d824ec11981ccad04af1cd1e4ce29 since it is not
technically sound.

[llvm] Remove unused local variables (NFC) (#138467)

2025-05-04T20:05:18+00:00

[AMDGPU] remove move instruction if there is no user of it (#136735)

2025-05-03T06:23:52+00:00

Co-authored-by: Baoshan Pang

[AMDGPU] Unused sdst writing to null (#133229)

2025-03-28T17:12:34+00:00

Unused sdst writing to null to avoid a false VALU->SALU dependency
stall. This requires using the VOP3 encoding.

[AMDGPU][True16][CodeGen] true16 codegen pattern for fma (#127240)

2025-02-19T16:37:24+00:00

Previous PR https://github.com/llvm/llvm-project/pull/122950 get
reverted since it hit the buildbot failure. Another patch get merged
when this PR is under review, and thus causing one test not up to date.

repen this PR and fixed the issue.

Revert "[AMDGPU][True16][CodeGen] true16 codegen pattern for fma (#12… (#127175)

2025-02-14T07:28:45+00:00

Reverting this patch since it raise buildbot failure

This reverts commit 2a7487cc2e0fb8bd91784e2d9636a65baa6d90ed.

[AMDGPU][True16][CodeGen] true16 codegen pattern for fma (#122950)

2025-02-14T07:16:00+00:00

true16 codegen pattern for f16 fma.

created a duplicated shrink-mad-fma-gfx10.mir from shrink-mad-fma to
seperate pre-GFX11 and GFX11 mir test.