mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-06-13 08:28:55 +08:00
8c174bdad4
* wmma * p2 * test * left * work * pickle * handwritten failing tests * start work * test the pipes * empirical evidence * update rdna4 enum types * VALU pipe 1 * TRANSCENDENTAL pipe * transcendental function units * reorder * wmma pipe * cleanup and notes * smaller * work * diff cleanup * pickle * use se:1 * int
SQTT Profiling
Getting SQ Thread Trace
VIZ=2 to enable SQTT profiling.
SQTT_ITRACE_SE_MASK=X to select shader engines for instruction tracing, -1 = all, 0 = disabled, >0 = SE bitmask, default 0b11.
SQTT_BUFFER_SIZE=X to change size of SQTT buffer (per shader engine, 6 SEs on 7900xtx) in megabytes, default 256.
Viewing the traces
- Web UI:
tinygrad/viz/serve.py - Command line:
python -m tinygrad.renderer.amd.sqtt