zjing14 04f93aadb8 Grouped conv bwd data with fp16 input and bf8fp8 comp (#962) ...

* Add f8 bf8 gemm example

* Add element-wise ops

* Add intrinsics

* Update reference calculation

* Add an additional type option for xdlops gemm

* Fix build process

* Add bf8 to buffer addressing

* Update blockwise op, split typeA and typeB

* Update for compatibility

* Uppdate naming to f8->fp8

* Update naming

* Format

* Update naming (#937)

* Add a client example

* Add computetypes to device and gridwise ops

* Add instances, update instance factory

* Format

* Fix a flag

* Add ckProfiler mode

* Fix typos

* Add an example

* Add bf8 generator

* add bf8 mfma; fixed type_convert for bf8

* move verfication ahead of timing

* Update reference calculation

* Fix reference

* Narrow down float init range

* Fix bf8 bf8 mfma

* Add bf8 @ fp8 mfma

* Update example

* Update instances

* Update profiler api

* Update for compatibility

* Format

* Remove extra example

* Clean up

* workaround convert

* added instance of f16_bf8f8, and client example

* fixed mfma selector

* format

---------

Co-authored-by: Rostyslav Geyyer <rosty.geyyer@amd.com>
Co-authored-by: Rostyslav Geyyer <46627076+geyyer@users.noreply.github.com>
Co-authored-by: Jing Zhang <jizha@amd.com>

2023-10-04 18:04:27 -05:00

..

impl

Grouped conv bwd data with fp16 input and bf8fp8 comp (#962)

2023-10-04 18:04:27 -05:00

conv_tensor_rearrange_op.hpp

Add column to image kernel (#930)

2023-09-27 17:19:06 +02:00

convolution_backward_data_specialization.hpp

Grouped 3d conv backward data support (#799)

2023-07-18 11:01:33 -05:00

convolution_backward_weight_specialization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

convolution_forward_specialization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_avgpool_bwd.hpp

Average pool backward deviceOP and example (#797)

2023-08-10 12:04:35 +08:00

device_base.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_contraction_multiple_d.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_gemm_e_permute.hpp

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

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

device_batched_gemm_gemm.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_gemm_multi_d.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_gemm_multiple_d_gemm_multiple_d.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_gemm_softmax_gemm_permute.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_gemm_softmax_gemm.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batched_gemm.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batchnorm_backward.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batchnorm_forward.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_batchnorm_infer.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_cgemm.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_contraction_multiple_abd.hpp

Contraction multi abd (#957)

2023-10-02 09:18:36 -05:00

device_contraction_multiple_d.hpp

Add support for mixed precision in contraction scale and bilinear (#936)

2023-09-29 10:54:31 -05:00

device_conv_bwd_data.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_conv_fwd_bias_activation_add.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_conv_fwd_bias_activation.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_conv_fwd.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_conv_tensor_rearrange.hpp

Add column to image kernel (#930)

2023-09-27 17:19:06 +02:00

device_elementwise_normalization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_elementwise.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_bias_e_permute.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_multiple_abd.hpp

Add multiple A/B support (#906)

2023-09-26 21:16:23 -05:00

device_gemm_multiple_d_layernorm.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_multiple_d_multiple_r.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_multiple_d.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_reduce.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_splitk.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_gemm_streamk.hpp

initial stream-k implementation with example (#699)

2023-07-26 14:18:15 -05:00

device_gemm.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_grouped_contraction_multiple_d.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_grouped_conv_bwd_data_multiple_d.hpp

Grouped conv bwd data with fp16 input and bf8fp8 comp (#962)

2023-10-04 18:04:27 -05:00

device_grouped_conv_bwd_weight.hpp

Add conv bwd weight fp16 comp bf8 fp8 op, instances and example (#945)

2023-10-04 08:19:08 -05:00

device_grouped_conv_fwd_multiple_d.hpp

3d grouped conv fwd with input/output fp16 and comp fp8 (#931)

2023-10-03 20:04:26 -05:00

device_grouped_conv_fwd.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_grouped_gemm_fixed_nk.hpp

Grouped Gemm with Fixed K and N with SplitK (#818)

2023-08-31 09:22:12 -05:00

device_grouped_gemm_softmax_gemm_permute.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_grouped_gemm_splitk.hpp

Grouped Gemm + SplitK + simplified Kernel Args (#669)

2023-04-24 15:43:36 -05:00

device_grouped_gemm.hpp

Multiple fixes to GroupedGemm+SplitK (#707)

2023-05-30 07:09:06 -05:00

device_max_pool_bwd.hpp

MaxPool & AvgPool bwd instances, test, ckProfiler, client example (#861)

2023-08-31 21:01:50 +08:00

device_multiple_reduce.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_normalization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_permute.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_pool_fwd.hpp

Refactor pool fwd (#815)

2023-08-15 02:25:28 +08:00

device_put_element.hpp

Average pool backward deviceOP and example (#797)

2023-08-10 12:04:35 +08:00

device_reduce.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

device_softmax.hpp

Padded Generic Kernel Instance (#730)

2023-06-16 23:43:11 -05:00

device_splitk_contraction_multiple_d.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

gemm_specialization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

masking_specialization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

matrix_padder.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

reduction_operator_mapping.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

tensor_layout.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

tensor_specialization.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00

welford_helper.hpp

update copyright headers (#726)

2023-05-31 18:46:57 -05:00