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

b2b bias vector support (#482)

Browse Source 
* b2b bias vector support

* add files

Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
Haicheng Wu
2022-04-30 04:16:15 -07:00
committed by GitHub
co-authored by Haicheng Wu
parent 86ce09aed1
commit ec2b4fd85d
34 changed files with 1096 additions and 324 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/13_two_tensor_op_fusion/README.md
+23
View File
@@ -61,6 +61,29 @@ When applying the above constraint to convolutions, it is required that the 2nd
kernel doesn't have halos such that data used by each threadblock doesn't depend on any other
threadblock. Typically this requires the 2nd Convolution uses 1x1 filter without any paddings.
# Build and run
- Run cmake at top-level CUTLASS
- `make 13_two_tensor_op_fusion`
- Run individual benchmarks
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_f16_sm75_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_f16_sm75_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_f16_sm80_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_f16_sm80_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_s8_sm75_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_s8_sm75_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_s8_sm80_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_convs_s8_sm80_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_f16_sm75_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_f16_sm75_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_f16_sm80_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_f16_sm80_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_s8_sm75_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_s8_sm75_shmem`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_s8_sm80_rf`
- `./examples/13_two_tensor_op_fusion/13_fused_two_gemms_s8_sm80_shmem`
# Copyright
Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.