Anthony Chang 31cacabafa Attention with output permutation (#370) ...

* comment on specialization for TensorSpecialization::Packed

* gemm_softmax_gemm with output permutation

* scaling

* refactor MatrixPadder; rename to GemmPadder

* remove old sanity check

* restore original gemm_softmax_gemm

* revise comment in gemm_softmax_gemm example

* use GetElementSpaceSize()

* remove extra header

* typo

* remove archaic DeviceOpPtr

[ROCm/composable_kernel commit: e0d8806ca1]

2022-08-23 14:52:56 -05:00

..

01_gemm

Fused GEMM+GEMM (#351)

2022-08-13 09:18:58 -05:00

02_gemm_bilinear

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

03_gemm_bias_relu

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

04_gemm_add_add_fastgelu

Add example of Gemm + AddAddFastGelu (data type: int4) (#369)

2022-08-23 10:38:41 -05:00

09_convnd_fwd

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

12_reduce

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

2022-08-13 01:10:01 -05:00

13_pool2d_fwd

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

14_gemm_xdl_requant_relu_requant

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

15_grouped_gemm

Add examples of batched/grouped/SplitK Gemm for int8/bfp16/fp16/fp32 (#361)

2022-08-23 14:41:56 -05:00

16_gemm_multi_d_multi_reduces

[What] Fix bug of verification fail on E Matrix (#371)

2022-08-22 07:50:28 -05:00

17_convnd_bwd_data

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

18_batched_gemm_reduce

Fused attention (#345)

2022-08-13 00:16:14 -05:00

19_binary_elementwise

Batchnorm-forward and Batchnorm-infer Implemented using generic kernels (#320)

2022-08-15 10:11:02 -05:00

20_convnd_bwd_weight

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

21_gemm_layernorm

Batchnorm-forward and Batchnorm-infer Implemented using generic kernels (#320)

2022-08-15 10:11:02 -05:00

22_cgemm

CGEMM examples bf16, fp32, int8 (#332)

2022-08-02 14:52:27 -05:00

23_softmax

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

24_batched_gemm

Add examples of batched/grouped/SplitK Gemm for int8/bfp16/fp16/fp32 (#361)

2022-08-23 14:41:56 -05:00

24_batched_gemm_e_permute

Add examples of batched/grouped/SplitK Gemm for int8/bfp16/fp16/fp32 (#361)

2022-08-23 14:41:56 -05:00

25_gemm_bias_e_permute

add g; fixed strides (#355)

2022-08-12 15:22:39 -05:00

26_contraction

Clean up conv example, Instances, profiler and test (#324)

2022-07-29 18:19:25 -05:00

27_layernorm

Layernorm welford (#346)

2022-08-13 09:43:18 -05:00

28_grouped_gemm_bias_e_permute

Add batched/grouped_gemm contraction deviceOps (#349)

2022-08-10 12:20:29 -05:00

29_batched_gemm_bias_e_permute

Add batched/grouped_gemm contraction deviceOps (#349)

2022-08-10 12:20:29 -05:00

30_grouped_convnd_fwd_bias_relu_add

Fused GEMM+GEMM (#351)

2022-08-13 09:18:58 -05:00

31_batched_gemm_gemm

Attention with output permutation (#370)

2022-08-23 14:52:56 -05:00

32_batched_gemm_scale_softmax_gemm

Attention with output permutation (#370)

2022-08-23 14:52:56 -05:00

33_multiple_reduce

Batchnorm-forward and Batchnorm-infer Implemented using generic kernels (#320)

2022-08-15 10:11:02 -05:00

34_batchnorm

Batchnorm-forward and Batchnorm-infer Implemented using generic kernels (#320)

2022-08-15 10:11:02 -05:00

35_splitK_gemm

Add examples of batched/grouped/SplitK Gemm for int8/bfp16/fp16/fp32 (#361)

2022-08-23 14:41:56 -05:00

CMakeLists.txt

Add examples of batched/grouped/SplitK Gemm for int8/bfp16/fp16/fp32 (#361)

2022-08-23 14:41:56 -05:00