Skip to content

[WaveTransform] Tests with non-trivial CodeGen diff#2595

Open
TejaX-Alaghari wants to merge 1 commit into
amd-feature/wave-transformfrom
amd/dev/tmahatej/wave-transform/possible-incorrect-branching
Open

[WaveTransform] Tests with non-trivial CodeGen diff#2595
TejaX-Alaghari wants to merge 1 commit into
amd-feature/wave-transformfrom
amd/dev/tmahatej/wave-transform/possible-incorrect-branching

Conversation

@TejaX-Alaghari
Copy link
Copy Markdown

@TejaX-Alaghari TejaX-Alaghari commented May 19, 2026

This PR highlights the tests that need a closer review in evaluating the CodeGen in LWT flow

  • llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.16bit.ll
  • llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
  • llvm/test/CodeGen/AMDGPU/av-split-dead-valno-crash.ll
  • llvm/test/CodeGen/AMDGPU/bug-sdag-emitcopyfromreg.ll

@z1-cciauto
Copy link
Copy Markdown
Collaborator

@TejaX-Alaghari TejaX-Alaghari requested a review from vg0204 May 19, 2026 09:09
@TejaX-Alaghari TejaX-Alaghari force-pushed the amd/dev/tmahatej/wave-transform/possible-incorrect-branching branch from 6e41975 to 482e781 Compare May 19, 2026 09:54
@TejaX-Alaghari TejaX-Alaghari changed the title [WaveTransform] Tests with non-trivial diff in branching [WaveTransform] Tests with non-trivial CodeGen diff May 19, 2026
@z1-cciauto
Copy link
Copy Markdown
Collaborator

; GFX11-TRUE16-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; GFX11-TRUE16-NEXT: s_xor_b32 s0, exec_lo, s0
; GFX11-TRUE16-NEXT: ; %bb.1: ; %cmp.false
; GFX11-TRUE16-NEXT: v_mov_b16_e32 v1.l, v0.l
Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The %cmp.false block is entirely removed in LWT flow.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants