Philippe Tillet d62e581ab3 basic split-k across warps working for GEMM

2019-08-05 19:33:28 -07:00

..

alignment_info.cpp

[codegen/optimize_dce.cpp] fixed bugs whereby barriers were removed by DCE

2019-07-31 15:11:10 -07:00

optimize_dce.cpp

[codegen/optimize_dce.cpp] fixed bugs whereby barriers were removed by DCE

2019-07-31 15:11:10 -07:00

optimize_dot.cpp

basic split-k across warps working for GEMM

2019-08-05 19:33:28 -07:00

optimize_trans.cpp

[ir] deleted mask/merge instructions; will be replaced by masked_load/store and select

2019-07-25 15:06:15 -07:00

reassociate.cpp

[codegen/reassociation] now recursively takes pointer arguments into account as well

2019-07-31 18:41:56 -07:00

selection.cpp

basic split-k across warps working for GEMM

2019-08-05 19:33:28 -07:00

shmem_allocation.cpp

basic split-k across warps working for GEMM

2019-08-05 19:33:28 -07:00

shmem_barriers.cpp

[general] major overhaul of triton-c/triton-ir/triton-jit:

2019-04-25 16:18:15 -04:00

shmem_info.cpp

[dnn] Adding batchnorm

2019-07-08 18:44:37 -07:00

shmem_liveness.cpp

[general] major overhaul of triton-c/triton-ir/triton-jit:

2019-04-25 16:18:15 -04:00

target.cpp

[dnn/blocksparse] FPROP test passes!

2019-07-29 17:06:20 -07:00

tune.cpp

basic split-k across warps working for GEMM

2019-08-05 19:33:28 -07:00

vectorize.cpp

Reparameterized in terms of micro- and nano- tiles

2019-03-10 23:10:17 -04:00