ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-20 04:49:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add examples for reduction fp16/fp32/bp16/int8/fp64 for 3d/4d/5d (#342)

Browse Source 
* Update the reduce_blockwise example to support user specified data type and input+reducing dimensions

* Add examples for using reduce_multiblock_atomic_add

* Add more running examples to the default command-line

* Remove un-necessary header including

* Update to the example README.md

[ROCm/composable_kernel commit: 14932e8de3]
This commit is contained in:
Qianfeng
2022-08-13 14:10:01 +08:00
committed by GitHub
parent ada72bead2
commit 23dc96e13c
7 changed files with 952 additions and 243 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
example/12_reduce/README.md
View File

@@ -2,20 +2,41 @@
## Run ```example_reduce_blockwise```
```bash
# -D <xxx> : input 4-d tensor lengths
# -D <xxx> : input 3d/4d/5d tensor lengths
# -R <xxx> : reduce dimension ids
# -v <x> : verification (0=no, 1=yes)
#arg1: initialization (0=no init, 1=single integer value, 2=scope integer value, 3=decimal value)
#arg2: time kernel (0=no, 1=yes)
./bin/example_reduce_blockwise -D 16,64,32,960 -v 1 1 1
#arg1: data type (0: fp16, 1: fp32, 3: int8, 5: bp16, 6: fp64, 7: int4)
#arg2: initialization (0=no init, 1=single integer value, 2=scope integer value, 3=decimal value)
#arg3: time kernel (0=no, 1=yes)
./bin/example_reduce_blockwise -D 16,64,32,960 -v 1 0 2 1
```
Result
```
./bin/example_reduce_blockwise -D 16,64,32,960 -v 1 1 1
launch_and_time_kernel: grid_dim {240, 1, 1}, block_dim {256, 1, 1}
./bin/example_reduce_blockwise -D 16,64,32,960 -v 1 0 2 1
launch_and_time_kernel: grid_dim {240, 1, 1}, block_dim {256, 1, 1}
Warm up 1 time
Start running 10 times...
Perf: 0.282592 ms, 222.641 GB/s, DeviceReduceBlockWise<256,M_C4_S1,K_C64_S1,InSrcVectorDim_0_InSrcVectorSize_1_OutDstVectorSize_1>
Perf: 0.238063 ms, 264.285 GB/s, DeviceReduceBlockWise<256,M_C4_S1,K_C64_S1,InSrcVectorDim_0_InSrcVectorSize_1_OutDstVectorSize_1>
```
## Run ```example_reduce_multiblock_atomic_add```
```bash
# -D <xxx> : input 3d/4d/5d tensor lengths
# -R <xxx> : reduce dimension ids
# -v <x> : verification (0=no, 1=yes)
#arg1: data type (0: fp32, 1: fp64)
#arg2: initialization (0=no init, 1=single integer value, 2=scope integer value, 3=decimal value)
#arg3: time kernel (0=no, 1=yes)
./bin/example_reduce_multiblock_atomic_add -D 16,64,32,960 -v 1 0 2 0
```
Result
```
./bin/example_reduce_multiblock_atomic_add -D 16,64,32,960 -v 1 0 2 0
Perf: 0 ms, inf GB/s, DeviceReduceMultiBlock<256,M_C4_S1,K_C64_S1,InSrcVectorDim_0_InSrcVectorSize_1_OutDstVectorSize_1>
echo $?
0
```
# Instructions for ```example_reduce_blockwise_two_call```