Adam Osewski b4032629e5 Grouped GEMM Multiple D tile loop. (#1247) ...

* Overload output stream operator for LoopScheduler and PiplineVersion

* Add Run overload accepting grid descriptors MK.

* Add __device__ keyword for CalculateGridSize

* Create device op GroupedGemmMultipleD

* Add GroupedGemm MultipleD Tile Loop implementation.

* Add an example for GroupedGemm MultipleD tile loop.

* Device Op GroupedGEMMTileLoop.

* Bunch of small changes in exmaple.

* CkProfiler

* Remove unused tparam.

* Fix include statement.

* Fix output stream overloads.

* Do not make descriptors and check validity untill we find group.

* Fix gemm desc initialization.

* Revert device op

* Fix compilation for DTYPES=FP16

* Validate tensor transfers paramters.

* Validate on host only NK dims if M is not known.

* Fix bug.

* A convenient debug func for selecting threads.

* Fix has main k block loop bug.

* Make sure that b2c has up to date tile offset.

* Output stream operator for Sequence type.

* Cmake file formatting.

2024-04-25 15:12:53 -05:00

..

impl

Grouped GEMM Multiple D tile loop. (#1247)

2024-04-25 15:12:53 -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

Fixed GroupedGemmFixedNK with hipGraph (#1065)

2023-11-30 15:09:27 -06:00

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

Add contraction_multi_abd (#972)

2023-10-17 20:17:58 -05:00

device_contraction_multiple_d.hpp

Add support for mixed precision in contraction scale and bilinear (#973)

2023-11-02 14:26:33 -07:00

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 support for groups in Img2Col/Col2Img (#1007)

2023-10-31 10:46:32 +01:00

device_elementwise_normalization.hpp

update copyright headers (#726)

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

device_elementwise_scale.hpp

Refactor elementwise kernels (#1222)

2024-04-19 13:31:17 +02:00

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_dequantB.hpp

Navi3 rel (#1176)

2024-03-08 17:11:51 -08:00

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

Add splitk gemm fp16 @ fp16 with fp8 compute instances (#983)

2023-10-13 16:27:11 -05:00

device_gemm_streamk.hpp

initial stream-k implementation with example (#699)

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

device_gemm_v2.hpp

[GEMM] Gemm universal device operation (#1154)

2024-04-13 21:03:18 -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_multiple_d.hpp

Add grouped conv bwd weight multi d kernel (#1237)

2024-04-18 23:35:04 +02:00

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_abd.hpp

Add instances for conv_scale with fp8@bf8->fp8 (#1220)

2024-04-03 09:08:08 -05:00

device_grouped_conv_fwd_multiple_d.hpp

Introduce multiABD api and deprecate multiD (#1035)

2023-11-14 17:00:40 +01:00

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_multi_abd_fixed_nk.hpp

Added Multi_ABD support into Gemm and GroupedGemmFixedNK (#978)

2024-04-15 21:09:45 -05:00

device_grouped_gemm_multi_abd.hpp

Added Multi_ABD support into Gemm and GroupedGemmFixedNK (#978)

2024-04-15 21:09:45 -05:00

device_grouped_gemm_multiple_d_splitk.hpp

Add Grouped Gemm Multiple D SplitK TwoStage (#1212)

2024-04-04 11:01:33 +02:00

device_grouped_gemm_softmax_gemm_permute.hpp

update copyright headers (#726)

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

device_grouped_gemm_splitk.hpp

Revert "Grouped Gemm with looping over the tiles. (#788)" (#982)

2023-10-11 14:27:29 -05:00

device_grouped_gemm_tile_loop.hpp

Grouped GEMM Multiple D tile loop. (#1247)

2024-04-25 15:12:53 -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_bwd_data.hpp

layernorm and groupnorm backward data (#1083)

2023-12-19 04:23:11 +08:00

device_normalization_bwd_gamma_beta.hpp

Backward of gamma and beta for layernorm and groupnorm (#1013)

2023-11-10 18:02:03 +08:00

device_normalization_fwd.hpp

Layernorm4d (#1022)

2023-11-09 08:34:51 +08:00

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

Revert "Grouped Gemm with looping over the tiles. (#788)" (#982)

2023-10-11 14:27:29 -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

Navi3 rel (#1176)

2024-03-08 17:11:51 -08:00

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

Support broadcast for bias in grouped conv fwd (#1081)

2023-12-08 11:07:42 +01:00

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