SQTT profiling (#9278)

* sqtt

* docs

* multi-device

* ProfileSQTTEvent

* exec update

* 256mb default

* don't let people hang their gpus

* bitfields from autogen

* asic info from mesa

* more bitfields from autogen

* SQTT_ITRACE_SE_MASK

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
This commit is contained in:
uuuvn
2025-03-11 10:19:56 +05:00
committed by GitHub
parent 2780e2027e
commit e85001b6ee
9 changed files with 3164 additions and 9 deletions

View File

@@ -118,12 +118,15 @@ jobs:
cp tinygrad/runtime/autogen/hsa.py /tmp/hsa.py.bak
cp tinygrad/runtime/autogen/comgr.py /tmp/comgr.py.bak
cp tinygrad/runtime/autogen/amd_gpu.py /tmp/amd_gpu.py.bak
cp tinygrad/runtime/autogen/sqtt.py /tmp/sqtt.py.bak
./autogen_stubs.sh hsa
./autogen_stubs.sh comgr
./autogen_stubs.sh amd
./autogen_stubs.sh sqtt
diff /tmp/hsa.py.bak tinygrad/runtime/autogen/hsa.py
diff /tmp/comgr.py.bak tinygrad/runtime/autogen/comgr.py
diff /tmp/amd_gpu.py.bak tinygrad/runtime/autogen/amd_gpu.py
diff /tmp/sqtt.py.bak tinygrad/runtime/autogen/sqtt.py
- name: Verify Linux autogen
run: |
cp tinygrad/runtime/autogen/libc.py /tmp/libc.py.bak