Google Git
Sign in
llvm / llvm-project / 8823efe77dad40eaea63b539c4d3d1036587ceb0
commit8823efe77dad40eaea63b539c4d3d1036587ceb0[log] [tgz]
authorValery Pykhtin <valery.pykhtin@amd.com>Mon Oct 13 16:17:11 2025 +0200
committerGitHub <noreply@github.com>Mon Oct 13 16:17:11 2025 +0200
treea4282f10d23b679dbe43558f0406db5399935d5b
parenta80a6b31a721c8d73445c458f1ea2312d9262750 [diff]
[AMDGPU] Add register usage debug printing the point of maximum register pressure. (#161850)

Basically this allows to analyze "why so many VGPRs used?".

It prints all live registers at the point of maximum register pressure
and for each register its defs/uses are dumped.

Currently can be run before and after the scheduler but would be nice if
it can be ran inbetween any passes (not sure this is possible with
legacy pass-manager). Requires debug or built with asserts compiler.

Highly recommended to run with debug info to have debug locations for
instructions.

Example output:

```
*** Register pressure info (VGPRs) for _ZN7ck_tile6ken.... ***
Max pressure is 256 VGPRs at 41780e@BB.18 (LoopHdr BB.16, Depth 1): %9858:vreg_512_align2 = contract V_MFMA_F32_32X32X16_BF16_mac_vgprcd_e64 %10137:vreg_128_align2, %10141:vreg_128_align2, %9858:vreg_512_align2(tied-def 0), 0, 0, 0, implicit $mode, implicit $exec

Live registers with single definition (123 VGPRs):
  %10126:VReg_128_Align2, LiveMask 00000000000000FF (4 VGPRs)
    def 41600r@BB.18 (LoopHdr BB.16, Depth 1): undef %10126.sub0_sub1:vreg_128_align2 = DS_READ_B64_TR_B16 %478:vgpr_32, 15232, 0, implicit $exec :: (load (s64) from %ir.sunkaddr1314, !noalias !60, addrspace 3)
    def 41608r@BB.18 (LoopHdr BB.16, Depth 1): %10126.sub2_sub3:vreg_128_align2 = DS_READ_B64_TR_B16 %478:vgpr_32, 16320, 0, implicit $exec :: (load (s64) from %ir.sunkaddr1315, !noalias !60, addrspace 3)
    use 41848r@BB.18 (LoopHdr BB.16, Depth 1): %9856:vreg_512_align2 = contract V_MFMA_F32_32X32X16_BF16_mac_vgprcd_e64 %10126:vreg_128_align2, %10138:vreg_128_align2, %9856:vreg_512_align2(tied-def 0), 0, 0, 0, implicit $mode, implicit $exec
  %10136:VReg_128_Align2, LiveMask 00000000000000FF (4 VGPRs)
    def 41264r@BB.18 (LoopHdr BB.16, Depth 1): undef %10136.sub0_sub1:vreg_128_align2 = DS_READ_B64_TR_B16 %478:vgpr_32, 2176, 0, implicit $exec :: (load (s64) from %ir.sunkaddr1294, !noalias !60, addrspace 3)
    def 41272r@BB.18 (LoopHdr BB.16, Depth 1): %10136.sub2_sub3:vreg_128_align2 = DS_READ_B64_TR_B16 %478:vgpr_32, 3264, 0, implicit $exec :: (load (s64) from %ir.sunkaddr1295, !noalias !60, addrspace 3)
    use 41788r@BB.18 (LoopHdr BB.16, Depth 1): %9858:vreg_512_align2 = contract V_MFMA_F32_32X32X16_BF16_mac_vgprcd_e64 %10136:vreg_128_align2, %10140:vreg_128_align2, %9858:vreg_512_align2(tied-def 0), 0, 0, 0, implicit $mode, implicit $exec
  %10129:VReg_128_Align2, LiveMask 00000000000000FF (4 VGPRs)
...
Live registers with multiple definitions (133 VGPRs):
  %9856:VReg_512_Align2, LiveMask 00000000FFFFFFFF (16 VGPRs)
    def 16544r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def undef %9856.sub0_sub1:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16592r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub2_sub3:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16608r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub4_sub5:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16656r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub6_sub7:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16672r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub8_sub9:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16720r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub10_sub11:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16736r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub12_sub13:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def 16784r@BB.8: INLINEASM &"v_pk_mul_f32 $0, $1, $2" [sideeffect] [isconvergent] [attdialect], $0:[regdef:VReg_64_Align2], def %9856.sub14_sub15:vreg_512_align2, $1:[reguse:VReg_64_Align2], %4069:vreg_64_align2, $2:[reguse:VReg_64_Align2], %10159:vreg_64_align2, !52
    def use 41828r@BB.18 (LoopHdr BB.16, Depth 1): %9856:vreg_512_align2 = contract V_MFMA_F32_...
...
********** INTERVALS **********
...
********** MACHINEINSTRS **********
# Machine code for function _ZN7ck_tile6kentr...
```
3 files changed
tree: a4282f10d23b679dbe43558f0406db5399935d5b
  1. .ci/
  2. .github/
  3. bolt/
  4. clang/
  5. clang-tools-extra/
  6. cmake/
  7. compiler-rt/
  8. cross-project-tests/
  9. flang/
  10. flang-rt/
  11. libc/
  12. libclc/
  13. libcxx/
  14. libcxxabi/
  15. libsycl/
  16. libunwind/
  17. lld/
  18. lldb/
  19. llvm/
  20. llvm-libgcc/
  21. mlir/
  22. offload/
  23. openmp/
  24. orc-rt/
  25. polly/
  26. runtimes/
  27. third-party/
  28. utils/
  29. .clang-format
  30. .clang-format-ignore
  31. .clang-tidy
  32. .git-blame-ignore-revs
  33. .gitattributes
  34. .gitignore
  35. .mailmap
  36. CODE_OF_CONDUCT.md
  37. CONTRIBUTING.md
  38. LICENSE.TXT
  39. pyproject.toml
  40. README.md
  41. SECURITY.md
README.md

The LLVM Compiler Infrastructure

OpenSSF Scorecard OpenSSF Best Practices libc++

Welcome to the LLVM project!

This repository contains the source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and run-time environments.

The LLVM project has multiple components. The core of the project is itself called “LLVM”. This contains all of the tools, libraries, and header files needed to process intermediate representations and convert them into object files. Tools include an assembler, disassembler, bitcode analyzer, and bitcode optimizer.

C-like languages use the Clang frontend. This component compiles C, C++, Objective-C, and Objective-C++ code into LLVM bitcode -- and from there into object files, using LLVM.

Other components include: the libc++ C++ standard library, the LLD linker, and more.

Getting the Source Code and Building LLVM

Consult the Getting Started with LLVM page for information on building and running LLVM.

For information on how to contribute to the LLVM project, please take a look at the Contributing to LLVM guide.

Getting in touch

Join the LLVM Discourse forums, Discord chat, LLVM Office Hours or Regular sync-ups.

The LLVM project has adopted a code of conduct for participants to all modes of communication within the project.