ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-17 03:19:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
db4ce5413069595581cc2b7c01ae794b47923f15
composable_kernel/composable_kernel/include/utility
History
Chao Liu db4ce54130 DL GEMM fp32/fp16/int8 (#41) 
* add threadwise copy the copy a tensor in one copy, added kpack to DL GEMM

* add kpack into fwd v4r5 nchw fp32

[ROCm/composable_kernel commit: b8b2d0a6d1]
2021-07-04 22:50:29 -05:00
..
amd_buffer_addressing_v2.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
amd_buffer_addressing.hpp
Overhaul vector_type and use real vector for int8x4_t instead of aliasing from int32_t (#29)
2021-04-12 23:48:43 -05:00
amd_dlop.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
amd_inline_asm.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
amd_llvm_intrinsic.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
amd_xdlops.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
array_multi_index.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
array.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
common_header.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
config.amd.hpp.in
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
config.nvidia.hpp.in
Code clean up (#20)
2020-06-23 20:31:27 -05:00
container_element_picker.hpp
No raw index calculation (#31)
2021-05-11 00:09:25 -05:00
container_helper.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
data_type.hpp
No raw index calculation (#31)
2021-05-11 00:09:25 -05:00
dynamic_buffer.hpp
DL GEMM fp32/fp16/int8 (#41)
2021-07-04 22:50:29 -05:00
float_type.amd.hpp.in
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
float_type.nvidia.hpp.in
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
functional2.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
functional3.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
functional4.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
functional.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
in_memory_operation.amd.hpp.in
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
in_memory_operation.nvidia.hpp.in
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
integral_constant.hpp
more utility code
2019-09-09 00:29:33 -05:00
magic_division.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
math.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
multi_index.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
number.hpp
more utility code
2019-09-09 00:29:33 -05:00
print.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
sequence_helper.hpp
Add online compilation for dynamic kernels (#37)
2021-06-24 08:34:19 -05:00
sequence.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
static_buffer.hpp
Use DynamicBuffer instead of raw pointer (#32)
2021-05-12 13:10:42 -05:00
statically_indexed_array_multi_index.hpp
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 (#36)
2021-06-09 23:53:08 -05:00
statically_indexed_array.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
synchronization.amd.hpp.in
Code clean up (#20)
2020-06-23 20:31:27 -05:00
synchronization.nvidia.hpp.in
Code clean up (#20)
2020-06-23 20:31:27 -05:00
tuple_helper.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00
tuple.hpp
xdlops_v4r4_fwd fp32/fp16 (#34)
2021-07-01 14:33:00 -05:00
type_helper.hpp
Add online compilation for dynamic kernels (#37)
2021-06-24 08:34:19 -05:00
type.hpp
Initial implementation of magic number division and "Merge" transformation that use it (#28)
2021-04-12 21:32:55 -05:00
utility.hpp
Dynamic tensor descriptor (#24)
2021-03-25 13:51:11 -05:00