Rostyslav Geyyer 42facfc6b7 Add conv bwd weight fp16 comp bf8 fp8 op, instances and example (#945) ...

* 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

---------

Co-authored-by: Jing Zhang <jizha@amd.com>

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

..

amd_address_space.hpp

update copyright headers (#726)

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

amd_buffer_addressing.hpp

Add fp8 @ bf8 gemm support and example (#933)

2023-10-02 16:39:03 -05:00

amd_gemm_dpp.hpp

Redesign the DPP8 GEMM kernel to use warp-wise component (#863)

2023-09-06 11:44:09 -05:00

amd_inline_asm.hpp

update copyright headers (#726)

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

amd_wave_read_first_lane.hpp

Fix incomplete object size (=4n + 3) support of amd_wave_read_first_lane() (#738)

2023-06-12 08:36:40 -05:00

amd_wmma.hpp

update copyright headers (#726)

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

amd_xdlops.hpp

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

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

array_multi_index.hpp

update copyright headers (#726)

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

array.hpp

update copyright headers (#726)

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

c_style_pointer_cast.hpp

update copyright headers (#726)

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

common_header.hpp

FP8 enablement - add a pseudorandom number generator, add conversion methods (#708)

2023-06-19 11:20:35 -05:00

container_element_picker.hpp

update copyright headers (#726)

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

container_helper.hpp

update copyright headers (#726)

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

data_type.hpp

Refactor f8_t, add bf8_t (#792)

2023-09-12 17:04:27 -05:00

debug.hpp

update copyright headers (#726)

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

dynamic_buffer.hpp

Add column to image kernel (#930)

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

enable_if.hpp

update copyright headers (#726)

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

f8_utils.hpp

Add native conversions fp8<->fp32 (#908)

2023-09-17 20:56:27 -05:00

functional2.hpp

update copyright headers (#726)

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

functional3.hpp

update copyright headers (#726)

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

functional4.hpp

update copyright headers (#726)

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

functional.hpp

update copyright headers (#726)

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

generic_memory_space_atomic.hpp

update copyright headers (#726)

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

get_id.hpp

update copyright headers (#726)

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

get_shift.hpp

Batchnorm splitk single kernel (#771)

2023-07-06 10:58:55 -05:00

ignore.hpp

update copyright headers (#726)

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

inner_product_dpp8.hpp

Redesign the DPP8 GEMM kernel to use warp-wise component (#863)

2023-09-06 11:44:09 -05:00

inner_product.hpp

Add grouped conv bwd weight dl instances and new layout (#897)

2023-09-13 10:14:31 -05:00

integral_constant.hpp

update copyright headers (#726)

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

is_detected.hpp

Add multiple A/B support (#906)

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

is_known_at_compile_time.hpp

update copyright headers (#726)

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

loop_scheduler.hpp

Redesign the DPP8 GEMM kernel to use warp-wise component (#863)

2023-09-06 11:44:09 -05:00

magic_division.hpp

initial stream-k implementation with example (#699)

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

math_v2.hpp

update copyright headers (#726)

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

math.hpp

initial stream-k implementation with example (#699)

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

multi_index.hpp

update copyright headers (#726)

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

number.hpp

update copyright headers (#726)

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

random_gen.hpp

FP8 enablement - add a pseudorandom number generator, add conversion methods (#708)

2023-06-19 11:20:35 -05:00

reduction_common.hpp

Batchnorm splitk single kernel (#771)

2023-07-06 10:58:55 -05:00

reduction_enums.hpp

update copyright headers (#726)

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

reduction_functions_accumulate.hpp

update copyright headers (#726)

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

reduction_operator.hpp

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

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

sequence_helper.hpp

update copyright headers (#726)

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

sequence.hpp

update copyright headers (#726)

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

span.hpp

update copyright headers (#726)

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

static_buffer.hpp

update copyright headers (#726)

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

statically_indexed_array_multi_index.hpp

update copyright headers (#726)

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

statically_indexed_array.hpp

update copyright headers (#726)

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

synchronization.hpp

update copyright headers (#726)

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

thread_group.hpp

update copyright headers (#726)

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

transpose_vectors.hpp

update copyright headers (#726)

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

tuple_helper.hpp

update copyright headers (#726)

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

tuple.hpp

Add multiple A/B support (#906)

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

type_convert.hpp

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

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

type.hpp

update copyright headers (#726)

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

workgroup_barrier.hpp

initial stream-k implementation with example (#699)

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

workgroup_synchronization.hpp

Batchnorm splitk single kernel (#771)

2023-07-06 10:58:55 -05:00