178 Commits

Author	SHA1	Message	Date
MHYang	0e6a23258e	Fix clang-format	2025-04-24 09:09:18 +00:00
MHYang	c4b2d5074a	Implement prefetch and instruction schedule	2025-04-23 23:06:23 +00:00
Clement Lin	257a06ef54	Add the warp gemm option	2025-04-23 15:04:24 +08:00
Clement Lin	11d45259d4	Add more warp gemm policies for FA	2025-04-23 14:41:09 +08:00
Clement Lin	ce4061847b	Remove unused code	2025-04-23 13:59:36 +08:00
YC Lin	ef085f402d	[GEMM] Add define macro for unused a/b blk window	2025-04-23 13:27:32 +00:00
Clement Lin	35de33c57b	Add codegen instances ... The following examples have been tested for 04_codegen: ./bin/codegen_basic_flash_attention_fwd 1 1 64 4096 4096 256 256 ./bin/codegen_basic_flash_attention_fwd 1 1 64 4096 4096 64 64 ./bin/codegen_basic_flash_attention_fwd 1 1 64 4096 4096 32 32 ./bin/codegen_basic_flash_attention_fwd 1 1 64 4096 4096 128 128 ./bin/codegen_basic_flash_attention_fwd 1 1 64 2048 2048 128 128 ./bin/codegen_basic_flash_attention_fwd 1 1 64 512 512 128 128	2025-04-23 11:51:35 +08:00
BoboFang	068d9fdbf7	Add MakeBlock2TileMap in 04_codegen_flash_attention_fwd	2025-04-23 09:47:37 +00:00
BoboFang	1a91c220a1	Change the permission of FA CMakeList.txt to 644	2025-04-22 15:37:03 +00:00
BoboFang	0a1227a5e7	Fix error after clang-format	2025-04-22 15:24:55 +00:00
BoboFang	95a8ac00c6	Run clang-format in toy_example	2025-04-22 14:55:57 +00:00
MHYang	537c519224	Initialize instruction schedule	2025-04-22 14:47:23 +00:00
BoboFang	de097a54d6	Add cache-aware in flash attention	2025-04-22 13:55:21 +00:00
MHYang	30e4b12ef4	Merge fix for bank conflict into codegen FA	2025-04-21 16:50:56 +00:00
MHYang	252b72ec30	Fix bank conflict	2025-04-21 16:47:51 +00:00
YC Lin	8a6cc0e94b	[GEMM] Fix bWarpTile issue and remove redundant pipeline in BlockGemmPipeline	2025-04-21 16:44:23 +00:00
MHYang	77a96c7a82	Fix register spilling and K0 tile size issues	2025-04-18 10:15:17 +00:00
YC Lin	918d5b21bc	[GEMM] Fix num_loop issues	2025-04-16 03:06:54 +00:00
Clement Lin	67bd9e4bb3	Add generate.py for codegen	2025-04-14 18:13:44 +08:00
YC Lin	a664958e9d	[GEMM] Remove redundant GetBlockGemm	2025-04-14 03:29:27 +00:00
YC Lin	b5e48d5459	[GEMM] Implement local prefetch and refactor block gemm pipeline	2025-04-13 02:54:44 +00:00
Clement Lin	08b175fc91	Refactor flash_attention_fwd_traits_ for codegen	2025-04-12 02:17:53 +08:00
YC Lin	b7eedac71a	[GEMM] Merge universal_block_gemm into block_gemm	2025-04-11 16:09:29 +00:00
mhYang	44eaa337f6	Fix flash attention 1 tile case	2025-04-11 15:44:53 +00:00
Clement Lin	bfadc59277	Refactor FlashAttnArgs usage for codegen	2025-04-11 13:46:25 +08:00
Clement Lin	f3db7e4fb7	Add codegen test example	2025-04-10 22:30:59 +08:00
YC Lin	6fdf2bd896	[GEMM] Refactor GetStaticLdsSize and remove GetSmemSize	2025-04-10 14:22:22 +00:00
Clement Lin	04199bc0aa	Fix indentation	2025-04-10 09:13:12 +08:00
Clement Lin	3e61925277	Remove unused code	2025-04-09 15:08:09 +08:00
YC Lin	fd26846d61	[GEMM] Refactor block gemm, pipeline, and policy of instruction schedule opt	2025-04-09 03:19:10 +00:00
YC Lin	fe61498468	[Add] Add build option for generating assembly	2025-04-06 23:50:26 +00:00
YC Lin	aac02a92ac	[GEMM] Refactor block gemm and pipeline policy of instruction schedule	2025-04-06 23:37:29 +00:00
Clement Lin	9151a1fb42	Add flash_attention_fwd toy_example	2025-04-04 00:39:02 +08:00
mhYang	f28aabb42f	Update tile size and use slc	2025-04-02 12:23:23 +00:00
mhYang	d5531ab9c9	Fix add flops calculation	2025-04-01 19:13:18 +00:00
ClementLinCF	04513ca683	Create README.md	2025-04-01 09:11:29 +08:00
mhYang	d1dbc69eda	Use mfma 16x16x32	2025-03-31 23:18:22 +00:00
mhYang	ee28e965f2	Fix KERNEL_D config	2025-03-31 17:53:57 +00:00
YC Lin	68cd6609eb	[GEMM] Add pragma message for different MFMA options	2025-03-30 20:05:35 +00:00
YC Lin	a8027a5b2f	[GEMM] Fix print typos	2025-03-30 19:55:13 +00:00
Clement Lin	5af7efdec5	Fix indentation typo	2025-03-30 15:06:07 +08:00
Clement Lin	de9385ba51	[GEMM] Fix MFMA condition checks	2025-03-30 14:02:30 +08:00
Clement Lin	5dd8e4ae0c	[GEMM] Add new macor options check	2025-03-30 10:07:21 +08:00
Clement Lin	7bc473835e	[GEMM] Add macros for multiple optimization options	2025-03-29 22:58:51 +08:00
YC Lin	428bcdeb40	[GEMM] default MFMA config	2025-03-29 21:11:29 +00:00
YC Lin	9a0d9dfc0a	git push test	2025-03-29 21:09:00 +00:00
root	a3c6ca1761	[GEMM] fix MFMA configurations	2025-03-29 21:05:21 +00:00
mhYang	16a4e1585a	Adjust mfma schedule order	2025-03-28 18:32:12 +00:00
Clement Lin	5428f17ca2	[GEMM] Replace const auto with constexpr index_t	2025-03-28 17:39:49 +08:00
Clement Lin	4eb246f20c	[GEMM] Update cache-aware wg schedule	2025-03-28 17:31:19 +08:00