mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-01 20:21:23 +00:00
05292b3604
* Let fmha_fwd_v3() compatible with fmha_fwd() * Decouple get_fwd_blobs() and FmhaFwdKernel * Decouple compatibility checks from get_fwd_blobs() * Extract product feature checks out from get_fwd_blobs() * Remove duplicated code in factories and redundant checks * Remove FmhaFwdKernel<>::GetName() * Let FmhaFwdApiPool support pipelines with different mask_impl * Add tile setting for fmha fwd v3 pipeline * Add fwd v3 instances to tile_example_fmha_fwd manually * Remove unused function import * Undo irrelevant changes * Remove fwd v3 instances from tile_example_fmha_fwd * Finish fmha fwd v3 kernel instance codegen * Fix formatting * Remove unused F_idx attribute * Add is_generic_attention_mask<> traits * Add constraints to the fmha fwd v3 pipeline * Unify traits & problem used for fmha fwd v3 * Unify kernel launch code for fmha fwd v2 & v3 * Unify kernel template selection logic * Use same kernel codegen template for both v2 & v3 * Rename api() property as render() method * Allow specifying filter for fmha fwd api pool * Allow specifying function name when rendering api pool items * Separate fmha fwd v3 kernel dispatching logic from v2 * Remove lambda assignment * Add simple v2/v3 dispatch logic * Stop generating empty if-clauses Skip iterating over dictionaries that have no traits, and avoid assigning i_* to them. * Use "".join() to concatenate fmha fwd api string content * Add more feature checks for fmha fwd v3 pipeline * Check features before dispatch to fmha_fwd_v3() * Add more feature checks for fmha_fwd_v3() * Add missing filter call * Use Tuple to reserve the dtype orders * Fix wrong pipeline matching logic * Add fmha fwd v3 group mode instances * Add functor_transform<> * Add type constraints to make_tile_window() * Remove fmha fwd v3 example * Fix wrong product(aiter mha_fwd()) config * Fix wrong fmha fwd v2/v3 selection logic * Fix formatting * Add comment to warning v3 kernel users * Fix wrong codegen logics * Remove unnecessary param * Fix format --------- Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
107 lines
3.2 KiB
Python
107 lines
3.2 KiB
Python
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
from datetime import datetime
|
|
import pathlib
|
|
from pathlib import Path
|
|
import subprocess
|
|
import os
|
|
import copy
|
|
|
|
NS = "ck_tile"
|
|
OPS = "ops"
|
|
OPS_COMMON = "common" # common header will be duplicated into ops/* other module
|
|
|
|
IGNORED_DIRS = ["utility", "ref"]
|
|
HEADER_COMMON = f"""// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-{datetime.now().year}, Advanced Micro Devices, Inc. All rights reserved.\n
|
|
"""
|
|
|
|
|
|
# aa/bb/cc/file.hpp -> (aa, bb, cc, file.hpp)
|
|
def get_module(f, level=0):
|
|
all_parts = f.parts
|
|
return str(all_parts[level])
|
|
|
|
|
|
all_files = []
|
|
for p in sorted(Path("./").rglob("*")):
|
|
if p.suffix == ".hpp":
|
|
all_files.append(pathlib.PurePath(p))
|
|
|
|
|
|
class submodule_t:
|
|
def __init__(self):
|
|
self.m = dict()
|
|
|
|
def push(self, f):
|
|
if len(f.parents) != 1: # ignore ./xxx.hpp
|
|
mod = get_module(f)
|
|
# Should only be included by demand
|
|
if mod in IGNORED_DIRS:
|
|
return
|
|
if mod == OPS:
|
|
if mod not in self.m.keys():
|
|
self.m[mod] = dict()
|
|
mod2 = get_module(f, 1)
|
|
if Path(mod2).suffix != ".hpp":
|
|
# ignore ops/xxx.hpp
|
|
if mod2 not in self.m[mod].keys():
|
|
self.m[mod][mod2] = list()
|
|
self.m[mod][mod2].append(f)
|
|
else:
|
|
if mod not in self.m.keys():
|
|
self.m[mod] = list()
|
|
self.m[mod].append(f)
|
|
|
|
def gen(self):
|
|
def gen_header(hpath, include_list):
|
|
# print(hpath)
|
|
if os.path.exists(str(hpath)):
|
|
os.remove(str(hpath))
|
|
with hpath.open("w") as f:
|
|
f.write(HEADER_COMMON)
|
|
f.write("#pragma once\n")
|
|
f.write("\n")
|
|
for individual_header in include_list:
|
|
header_path = NS + "/" + str(individual_header)
|
|
f.write(f'#include "{header_path}"\n')
|
|
# f.write('\n') # otherwise clang-format will complain
|
|
|
|
# print(self.m)
|
|
# restructure common
|
|
for k, v in self.m.items():
|
|
if k == OPS and OPS_COMMON in v.keys():
|
|
common_list = copy.deepcopy(v[OPS_COMMON])
|
|
# v.pop(OPS_COMMON)
|
|
for km in v.keys():
|
|
if km != OPS_COMMON:
|
|
v[km].extend(common_list)
|
|
|
|
for k, v in self.m.items():
|
|
if k == OPS:
|
|
for km, kv in v.items():
|
|
gen_header(Path(k) / (f"{km}.hpp"), kv)
|
|
else:
|
|
gen_header(Path(f"{k}.hpp"), v)
|
|
|
|
|
|
submodule = submodule_t()
|
|
# formatting
|
|
format_procs = []
|
|
for x in all_files:
|
|
dos2unix = f"python3 -m dos2unix {str(x)} {str(x)}"
|
|
clang_format = f"clang-format -style=file -i {str(x)}"
|
|
# One process to avoid race conditions.
|
|
cmd = f"{dos2unix} && {clang_format}"
|
|
format_procs.append(
|
|
subprocess.Popen(cmd, shell=True, stdout=open(os.devnull, "wb"))
|
|
)
|
|
submodule.push(x)
|
|
|
|
# Wait for formatting to complete before generating headers.
|
|
for p in format_procs:
|
|
p.wait()
|
|
|
|
submodule.gen()
|