[llvm] AMDGPU/GlobalISel: Fix regBankLegalize rules for uniform cvt_pkrtz (PR #203283)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Jun 11 08:09:52 PDT 2026
github-actions[bot] wrote:
<!--PREMERGE ADVISOR COMMENT: Linux-->
# :penguin: Linux x64 Test Results
* 175435 tests passed
* 3469 tests skipped
* 1 test failed
## Failed Tests
(click on a test name to see its output)
### LLVM
<details>
<summary>LLVM.CodeGen/AMDGPU/scalar-float-sop2.ll</summary>
```
Exit Code: 1
Command Output (stdout):
--
# RUN: at line 2
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/llc -mtriple=amdgcn -mcpu=gfx1150 < /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll | /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck -check-prefixes=CHECK,GFX1150 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/llc -mtriple=amdgcn -mcpu=gfx1150
# note: command had no output on stdout or stderr
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck -check-prefixes=CHECK,GFX1150 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll
# note: command had no output on stdout or stderr
# RUN: at line 3
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/llc -mtriple=amdgcn -mcpu=gfx1150 -global-isel -new-reg-bank-select < /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll | /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck -check-prefixes=CHECK,GFX1150 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/llc -mtriple=amdgcn -mcpu=gfx1150 -global-isel -new-reg-bank-select
# .---command stderr------------
# | LLVM ERROR: No AMDGPU RegBankLegalize rules defined for opcode: %0:sgpr(s32) = G_AMDGPU_S_BUFFER_LOAD %1:sgpr(<4 x s32>), %2:sgpr(s32), 0 :: (dereferenceable invariant load (s32)) (in function: _amdgpu_ps_main)
# `-----------------------------
# error: command failed with exit status: 1
# executed command: /home/gha/actions-runner/_work/llvm-project/llvm-project/build/bin/FileCheck -check-prefixes=CHECK,GFX1150 /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll
# .---command stderr------------
# | /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll:196:16: error: CHECK-LABEL: expected string not found in input
# | ; CHECK-LABEL: fmac_f16_with_mov:
# | ^
# | <stdin>:732:10: note: scanning from here
# | fmac_f16: ; @fmac_f16
# | ^
# | <stdin>:746:9: note: possible intended match here
# | .set .Lfmac_f16.uses_vcc, 0
# | ^
# |
# | Input file: <stdin>
# | Check file: /home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/test/CodeGen/AMDGPU/scalar-float-sop2.ll
# |
# | -dump-input=help explains the following input dump.
# |
# | Input was:
# | <<<<<<
# | .
# | .
# | .
# | 727: .long 0
# | 728: .text
# | 729: .globl fmac_f16 ; -- Begin function fmac_f16
# | 730: .p2align 8
# | 731: .type fmac_f16, at function
# | 732: fmac_f16: ; @fmac_f16
# | label:196'0 X~~~~~~~~~~~~ error: no match found
# | 733: ; %bb.0:
# | label:196'0 ~~~~~~~~~
# | 734: s_fmac_f16 s0, s1, s2
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~
# | 735: s_delay_alu instid0(SALU_CYCLE_3)
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 736: v_mov_b32_e32 v0, s0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~
# | 737: ; return to shader part epilog
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | .
# | .
# | .
# | 741: .set .Lfmac_f16.num_vgpr, 1
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 742: .set .Lfmac_f16.num_agpr, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 743: .set .Lfmac_f16.numbered_sgpr, 3
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 744: .set .Lfmac_f16.num_named_barrier, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 745: .set .Lfmac_f16.private_seg_size, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 746: .set .Lfmac_f16.uses_vcc, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | label:196'1 ? possible intended match
# | 747: .set .Lfmac_f16.uses_flat_scratch, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 748: .set .Lfmac_f16.has_dyn_sized_stack, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 749: .set .Lfmac_f16.has_recursion, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 750: .set .Lfmac_f16.has_indirect_call, 0
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | 751: .section .AMDGPU.csdata,"", at progbits
# | label:196'0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# | .
# | .
# | .
# | >>>>>>
# `-----------------------------
# error: command failed with exit status: 1
--
```
</details>
If these failures are unrelated to your changes (for example tests are broken or flaky at HEAD), please open an issue at https://github.com/llvm/llvm-project/issues and add the `infrastructure` label.
https://github.com/llvm/llvm-project/pull/203283
More information about the llvm-commits
mailing list