wu-arch/kernels
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1cfab407117bc40a0ddd993dc8bbfa8503c7f84c
kernels/tests/regression
History
Hansung Kim 1cfab40711 flash: Do Oi rescale with PV 
Since Oi rescale has data dependency to previous Oi which gets produced
at the PV GEMM, both rescale+GEMM needs to be in a single pipeline stage
or otherwise it requires a stall.  So instead, compute only the
rescale factor in the online softmax stage and apply rescaling right
before PV.
2024-08-30 20:11:07 -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: Do Oi rescale with PV
2024-08-30 20:11:07 -07:00
flops
Add regression flops
2024-04-24 21:10:21 -07:00
idle
idle: Use barriers instead to hang the core
2024-06-22 01:37:00 -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
make non dma gemmini use 64x64 tile size
2024-06-19 17:45:01 -07:00
sgemm_gemmini_dma
fp16 kernel
2024-08-06 02:43:44 -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: Accept threads_per_threadblock in load_tile_to_smem
2024-08-29 21:43:57 -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
vecaddx
vecaddx: Hardcode args/input device address to match chipyard
2024-03-27 15:15:52 -07:00
common.mk
common.mk: Embed operand.c to ELF, track header dependency
2024-08-30 17:24:43 -07:00
Makefile
minor udpate
2023-11-27 02:21:47 -08:00