George HotzandGitHub e464442adf WMMA for 7900XTX (#1563) ...

* go

* hip no LRU

* work

* works

* 16 TFLOPS

* 29 TFLOPS

* 30 TFLOPS

* never mind, it's 60 TFLOPS

* fix metal WMMA

* put hip alloc back

2023-08-19 09:07:23 -07:00

..

.gitignore

updates from the chonker branch

2022-11-07 21:12:08 -08:00

amx.py

Revert "update editorconfig, enforce via CI (#1343)" (#1380)

2023-07-31 10:35:50 -07:00

cuda_matmul.py

FLOAT16 off works

2023-04-19 15:34:56 -07:00

gemm.c

Revert "update editorconfig, enforce via CI (#1343)" (#1380)

2023-07-31 10:35:50 -07:00

gemm.py

Revert "update editorconfig, enforce via CI (#1343)" (#1380)

2023-07-31 10:35:50 -07:00

hip_matmul.py

fast HIP gemm -> 100 TFLOPS (#1476)

2023-08-09 06:54:15 -07:00

metal_conv.py

Rdna (#776)

2023-05-16 05:33:57 -07:00

metal_matmul.py

good stuff from tensor cores branch (#1199)

2023-07-08 16:58:26 -07:00

simple_matmul.py

WMMA for 7900XTX (#1563)

2023-08-19 09:07:23 -07:00

tf_gemm.py

Add tensorflow GEMM benchmark script (#1000)

2023-06-18 10:57:45 -07:00

torch_gemm.py

faster RDNA assembly backend (#990)

2023-06-16 12:06:38 -07:00