[AMDGPU] Add sext_trunc in RegBankCombiner

[Pierre-vh]

No description provided.

[Pierre-vh]

• [GlobalISel] Combine redundant sext_inreg #131624
• [AMDGPU] Add sext_trunc in RegBankCombiner #131623 👈 (View in Graphite)
• [GlobalISel] Combine (sext (trunc x)) to (sext_inreg x) #131622
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[llvmbot]

@llvm/pr-subscribers-llvm-globalisel

@llvm/pr-subscribers-backend-amdgpu

Author: Pierre van Houtryve (Pierre-vh)

Changes

---

Full diff: https://github.com/llvm/llvm-project/pull/131623.diff

1 Files Affected:

• (modified) llvm/lib/Target/AMDGPU/AMDGPUCombine.td (+1-1)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
index a21505356274b..083ce48911689 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
@@ -181,5 +181,5 @@ def AMDGPURegBankCombiner : GICombiner<
    zext_trunc_fold, int_minmax_to_med3, ptr_add_immed_chain,
    fp_minmax_to_clamp, fp_minmax_to_med3, fmed3_intrinsic_to_clamp,
    identity_combines, redundant_and, constant_fold_cast_op,
-   cast_of_cast_combines]> {
+   cast_of_cast_combines, sext_trunc]> {
 }

[arsenm]

Missing test changes?

[Pierre-vh]

Test changes were in the previous diff in the stack, it should be fixed now.

[shiltian]

Hmm, I still can't see the test change?

[Pierre-vh]

Ah, this doesn't do anything at this stage. It's only helpful once we disable widening of i16 ops to i32 in CGP. Then this pattern can appear and it'll fold it.

This combine is tested in AArch64. Should I copy over a few simple test cases in the AMDGPU folder just to show the combine works in RegBankCombiner?

[shiltian]

@arsenm Is it a good idea here to test two passes in one test case?

[cdevadas]

Yes. It helps to capture the lowering at significant points during the codegen that are important to test in certain scenarios.

[Pierre-vh]

Merge activity

• Apr 14, 4:03 AM EDT: A user started a stack merge that includes this pull request via Graphite.
• Apr 14, 4:06 AM EDT: Graphite rebased this pull request as part of a merge.
• Apr 14, 4:10 AM EDT: Graphite rebased this pull request as part of a merge.
• Apr 14, 4:13 AM EDT: Graphite rebased this pull request as part of a merge.
• Apr 14, 4:15 AM EDT: A user merged this pull request with Graphite.