Chao Liu
f4acec502e
Restructure gridwise and blockwise GEMM, add tensor contraction and FWD-v4r5 ( #36 )
...
* experimenting magic number division
* overhauling fwd-v4r4 to clearly reflect transformation graph
* added fwd-v4r5
* bug fix for make_dynamic_naive_tensor_descriptor_aligned_v2
* bug fix and added sanity-check in transform_dynamic_tensor_descriptor
* added conv_driver_v2
[ROCm/composable_kernel commit: 30072aec37
2021-06-09 23:53:08 -05:00
Chao Liu
da8f48c6d6
Use DynamicBuffer instead of raw pointer ( #32 )
...
* Use DynamicBuffer to hold raw pointer (to global and LDS memory)
* add workaround for compiler issue (inefficient ISA) of ds_write for int8x4, int8x8, int8x16
[ROCm/composable_kernel commit: 78b987fbd6
2021-05-12 13:10:42 -05:00
Chao Liu
ce4662dbda
No raw index calculation ( #31 )
...
* Replace most raw index calculation to coordinate transformation
* Overhaul blockwise and threadwise GEMM
* Overhaul driver for gridwies GEMM kernel
Co-authored-by: Jing Zhang <jizhan@amd.com >
[ROCm/composable_kernel commit: 01055d95d9
2021-05-11 00:09:25 -05:00
Chao Liu
b4dbf677ce
Dynamic tensor descriptor ( #24 )
...
* support dynamic tensor descriptor
* use buffer load OOB feature for padding case
* add navi support
* add int8x4 inference kernel
Co-authored-by: Chao Liu <chao@ixt-rack-81.local.lan >
Co-authored-by: Jing Zhang <jizhan@amd.com >
[ROCm/composable_kernel commit: fcbb978828
2021-03-25 13:51:11 -05:00
Chao Liu
0eb214d1cd
Code clean up ( #20 )
...
* tuning para,
* testing on v100
* add fp16
* remove deprecated tensor descriptor
* sync with miopen
* update build script
Co-authored-by: Jing Zhang <jizhan@amd.com >
[ROCm/composable_kernel commit: 5c7cec1115
2020-06-23 20:31:27 -05:00
Chao Liu
8b51bc4b1d
Added bwd data v3r1 v4r1, tweaking v1 ( #10 )
...
* Added bwd data v3r1: breaking down compute into a series of load balanced GEMM, and launch in a single kernel
* Added bwd data v4r1: like v3r1, but launch GEMMs in multiple kernels
* Tweaked v1r1 and v1r2 (atomic) on AMD GPU
[ROCm/composable_kernel commit: c5da0377fb
2020-01-20 10:20:03 -06:00
Chao Liu
3799741fee
backward data ( #7 )
...
* enabled atomic add in tensor copy
* added gridwise GEMM
* added backward data conv using GEMM + atomic
* added backward data conv using GEMM, no atomic
[ROCm/composable_kernel commit: 8f5f64960e
2019-12-03 01:16:12 -06:00
Chao Liu
08f130fed1
Refactor for MIOpen integration ( #4 )
...
Refactor, so can bring multi-index transformation and padding support into MIOpen
[ROCm/composable_kernel commit: 52c3fe05be
2019-10-11 11:37:31 -05:00
Chao Liu
0342a42f47
enable hip compiler flag: -amdgpu-enable-global-sgpr-addr
...
[ROCm/composable_kernel commit: f58bf38445
2019-09-17 17:34:39 -05:00
Chao Liu
dd6fef3b9e
add script for doing Jack's ISA injection hack
...
[ROCm/composable_kernel commit: 0c83df668f
2019-08-21 14:29:13 -05:00
Chao Liu
dc2cdacd15
refactored implicit gemm v1r3
...
[ROCm/composable_kernel commit: 284e7bb317
2019-07-29 15:25:38 -05:00
Chao Liu
360f15cf24
refactored implicit gemm v1r3
...
[ROCm/composable_kernel commit: efd419ecbe
2019-07-29 15:01:01 -05:00
Chao Liu
3f33abf401
update compile script
...
[ROCm/composable_kernel commit: c15ff3c825
2019-07-03 16:03:12 -05:00
Chao Liu
99fc474d24
tested on P100
...
[ROCm/composable_kernel commit: dab2938937
2019-06-27 15:46:09 -05:00
Chao Liu
11c6b2ab9a
change build
...
[ROCm/composable_kernel commit: c82b833d8e
2019-06-12 10:47:25 -05:00
Jing Zhang
b6d7e5fd48
ds_read_offset
...
[ROCm/composable_kernel commit: 49d5af1002
2019-04-26 15:55:26 -05:00
Chao Liu
35140bbc9e
enabled ds_read_b128 and ds_write_b128 on hip c++
...
[ROCm/composable_kernel commit: e624df922d
2019-04-09 19:05:44 -05:00
Chao Liu
008c584abb
Merge branch 'master' into inline_asm_v2
...
[ROCm/composable_kernel commit: 605afd0fb6
2019-04-04 18:40:23 -05:00
Chao Liu
770c141f35
add script to extrac asm on hip
...
[ROCm/composable_kernel commit: 6166233e05
2019-04-03 10:36:18 -05:00
Chao Liu
9d61f2597a
add cuda extract_asm script
...
[ROCm/composable_kernel commit: e6c86f81b5
2019-04-02 20:26:58 -05:00
Chao Liu
fdb7d41661
cleaning up dead code
...
[ROCm/composable_kernel commit: bdbc0eaad1
2019-04-02 17:58:44 -05:00
