wu-arch/kernels
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
21b6655c101e18c4fdb20f10331be4946b6530ef
kernels/tests/regression
History
Hansung Kim 21b6655c10 sgemm_impl: Implement fast coalesced wmma_store 
Enables a fairer comparison between core-coupled tensor core to Hopper
tensor core, where the latter benefits from coalesced full-throughput
moveout to GMEM because it does not use the 1x2 interleaved register
mapping.  This means the result matrix will be stored swizzled in the
GMEM, without breaking correctness.
2024-10-29 22:34:22 -07:00
..
bad_apple
dma and demo kernels
2024-06-07 18:11:19 -07:00
basic
adding tensor regression test.
2023-11-14 05:37:46 -08:00
demo
adding opencl convolution benchmark
2023-11-14 22:31:30 -08:00
diverge
adding tensor regression test.
2023-11-14 05:37:46 -08:00
dogfood
Vortex 2.0 changes:
2023-11-10 02:47:05 -08:00
fence
adding tensor regression test.
2023-11-14 05:37:46 -08:00
flash_attention
flash: Optimize smem alloc for tcore for 8banks
2024-09-19 21:31:39 -07:00
flops
Add regression flops
2024-04-24 21:10:21 -07:00
idle
new unaligned access kernel, update idle kernel
2024-10-24 17:28:59 -07:00
io_addr
adding tensor regression test.
2023-11-14 05:37:46 -08:00
mstress
adding tensor regression test.
2023-11-14 05:37:46 -08:00
no_mf_ext
adding tensor regression test.
2023-11-14 05:37:46 -08:00
no_smem
adding tensor regression test.
2023-11-14 05:37:46 -08:00
printf
adding tensor regression test.
2023-11-14 05:37:46 -08:00
rickroll
dma and demo kernels
2024-06-07 18:11:19 -07:00
sgemm_gemmini
fp16 no dma kernel
2024-10-24 17:12:34 -07:00
sgemm_gemmini_dma
update gemmini dma kernel
2024-10-28 13:47:13 -07:00
sgemm_gemmini_duo
sgemm_gemmini_duo: Check in serialized kernel as separate file
2024-06-12 22:44:14 -07:00
sgemm_tcore
sgemm_impl: Implement fast coalesced wmma_store
2024-10-29 22:34:22 -07:00
sgemm_wg
Add args.bin to ELF
2024-06-06 15:19:39 -07:00
sgemmx
minor udpate
2023-11-27 02:21:47 -08:00
sort
adding tensor regression test.
2023-11-14 05:37:46 -08:00
unaligned
new unaligned access kernel, update idle kernel
2024-10-24 17:28:59 -07:00
vecaddx
vecaddx: Hardcode args/input device address to match chipyard
2024-03-27 15:15:52 -07:00
common.mk
common.mk: Switch to -Os to prevent branch code duplication
2024-09-07 15:49:19 -07:00
Makefile
minor udpate
2023-11-27 02:21:47 -08:00