Max Podkorytov 04efd282cf [CK-tile] unhardcode the number of LDS banks from universal gemm policy (#3130) ...

Fixes LDS bank conflicts on gfx950 for universal gemm v3 pipeline

Replaces hardcoded LDS layer calculations with dynamic computation using the new architecture helpers

Adds architecture-specific helper function get_n_lds_banks()

Changes function attributes from CK_TILE_HOST_DEVICE to CK_TILE_DEVICE in universal gemm policy

2025-10-31 11:58:11 -07:00

..

gemm_pipeline_ag_bg_cr_base.hpp

[CK_TILE] Multiple-ABD GEMM example (#2788)

2025-09-19 01:14:11 +02:00

gemm_pipeline_ag_bg_cr_comp_async_default_policy.hpp

[CK-Tile] functional support for transposed inputs in compute-bound double-lds-buffer pipeline with async loads from global memory to LDS (#2984)

2025-10-10 12:57:50 -07:00

gemm_pipeline_ag_bg_cr_comp_async.hpp

[CK-Tile][Async gemm] add missing sync and f8 inputs test cases (#3000)

2025-10-24 12:16:01 -07:00

gemm_pipeline_ag_bg_cr_comp_v3.hpp

Lwpck 3550: Implement and test fixed precision fp8 x bf8 (#2963)

2025-10-30 13:36:10 +01:00

gemm_pipeline_ag_bg_cr_comp_v4_default_policy.hpp

Fix the vector load & fix the gfx950 compv4 error (#2831)

2025-09-12 11:48:45 -07:00

gemm_pipeline_ag_bg_cr_comp_v4.hpp

Lwpck 3550: Implement and test fixed precision fp8 x bf8 (#2963)

2025-10-30 13:36:10 +01:00

gemm_pipeline_ag_bg_cr_comp_v5_default_policy.hpp

[CK_TILE] CK_TILE GEMM WMMA Support for GFX11/GFX12 (#2466)

2025-08-15 16:22:27 -07:00

gemm_pipeline_ag_bg_cr_comp_v5.hpp

Fix for Add the API to load SGPR (#2913)

2025-09-25 10:32:42 -07:00

gemm_pipeline_ag_bg_cr_comp_v6_default_policy.hpp

[CK_TILE] Blockwise GEMM pipeline v6 - port of v5 from old CK (#2955)

2025-10-13 13:57:37 +02:00

gemm_pipeline_ag_bg_cr_comp_v6.hpp

[CK_TILE] Blockwise GEMM pipeline v6 - port of v5 from old CK (#2955)

2025-10-13 13:57:37 +02:00

gemm_pipeline_ag_bg_cr_mem.hpp

Add Memory pipeline for AQuant Block Scale GEMM (#2987)

2025-10-08 17:22:30 -07:00

gemm_pipeline_ag_bg_cr_scheduler.hpp

Revert "Optimize fmha fwd decode & prefill for gfx950 (#2641)" (#2670)

2025-08-12 20:27:10 +08:00

gemm_pipeline_agmem_bgmem_creg_v1_default_policy.hpp

[CK_TILE] CK_TILE GEMM WMMA Support for GFX11/GFX12 (#2466)

2025-08-15 16:22:27 -07:00

gemm_pipeline_agmem_bgmem_creg_v1.hpp

[CK_TILE] Multiple-ABD GEMM example (#2788)

2025-09-19 01:14:11 +02:00

gemm_pipeline_agmem_bgmem_creg_v2_default_policy.hpp

Ck tile gemm cshuffle & CK Tile GEMM restructure (#1535)

2024-10-10 18:02:22 +08:00

gemm_pipeline_agmem_bgmem_creg_v2.hpp

[CK_TILE] Multiple-ABD GEMM example (#2788)

2025-09-19 01:14:11 +02:00

gemm_pipeline_problem.hpp

[CK_TILE] Update flatmm related kernels (#3022)

2025-10-22 22:36:11 +08:00

gemm_universal_pipeline_ag_bg_cr_policy.hpp

[CK-tile] unhardcode the number of LDS banks from universal gemm policy (#3130)

2025-10-31 11:58:11 -07:00

tile_gemm_shape.hpp

Merge flatmm Operator with universal gemm (#2434)

2025-07-11 08:27:55 -07:00

tile_gemm_traits.hpp

[CK_TILE] Multiple-ABD GEMM example (#2788)

2025-09-19 01:14:11 +02:00

wp_pipeline_agmem_bgmem_creg_base_policy.hpp

Add gemm weight preshuffle pk_int_t support (#2858)

2025-09-18 21:26:10 -07:00

wp_pipeline_agmem_bgmem_creg_v1.hpp

Add gemm weight preshuffle pk_int_t support (#2858)

2025-09-18 21:26:10 -07:00

wp_pipeline_agmem_bgmem_creg_v2.hpp

Add gemm weight preshuffle pk_int_t support (#2858)

2025-09-18 21:26:10 -07:00