leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

Fix typos 2 (#842)

Browse Source 
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
This commit is contained in:
Alexander Pivovarov
2023-03-09 23:22:56 -05:00
committed by GitHub
co-authored by Haicheng Wu
parent c4f6b8c6bc
commit 7e370c9637
161 changed files with 310 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/13_two_tensor_op_fusion/threadblock/b2b_implicit_gemm_pipelined.h
+2 -2
View File
@@ -321,7 +321,7 @@ public:
int smem_write_stage_idx = 1;
// Issue loads during the first warp-level matrix multiply-add *AFTER* issuing
// shared memory loads (which have the tighest latency requirement).
// shared memory loads (which have the tightest latency requirement).
//
// Mainloop
@@ -461,7 +461,7 @@ public:
int gemm_k_iterations_1 = FragmentIteratorA1::Policy::kIterations / Base::kWarpGemmIterations1;
// Issue loads during the first warp-level matrix multiply-add *AFTER* issuing
// shared memory loads (which have the tighest latency requirement).
// shared memory loads (which have the tightest latency requirement).
//
// Mainloop
examples/13_two_tensor_op_fusion/threadblock/b2b_implicit_gemm_pipelined_smem_accumulator.h
+1 -1
View File
@@ -341,7 +341,7 @@ public:
int smem_write_stage_idx = 1;
// Issue loads during the first warp-level matrix multiply-add *AFTER* issuing
// shared memory loads (which have the tighest latency requirement).
// shared memory loads (which have the tightest latency requirement).
//
// Mainloop
examples/13_two_tensor_op_fusion/threadblock/b2b_mma_pipelined.h
+1 -1
View File
@@ -325,7 +325,7 @@ public:
iterator_B0.clear_mask(gemm_k_iterations_0 <= 1);
// Issue loads during the first warp-level matrix multiply-add *AFTER* issuing
// shared memory loads (which have the tighest latency requirement).
// shared memory loads (which have the tightest latency requirement).
//
// Mainloop
examples/13_two_tensor_op_fusion/threadblock/b2b_mma_pipelined_smem_accumulator.h
+1 -1
View File
@@ -346,7 +346,7 @@ public:
iterator_B0.clear_mask(gemm_k_iterations_0 <= 1);
// Issue loads during the first warp-level matrix multiply-add *AFTER* issuing
// shared memory loads (which have the tighest latency requirement).
// shared memory loads (which have the tightest latency requirement).
//
// Mainloop