leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

New updates for 2.11 (#775)

Browse Source 
* New updates.

* Minor profiler updates

Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
This commit is contained in:
ANIKET SHIVAM
2023-01-20 16:32:57 -05:00
committed by GitHub
co-authored by Aniket Shivam
parent d49bef88f9
commit 66d9cddc83
1341 changed files with 2003 additions and 1732 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/40_cutlass_py/conv2d.py
+1 -1
View File
@@ -1,6 +1,6 @@
################################################################################
#
# Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
#
# Redistribution and use in source and binary forms, with or without
examples/40_cutlass_py/customizable/conv2d.py
+1 -1
View File
@@ -1,6 +1,6 @@
################################################################################
#
# Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
#
# Redistribution and use in source and binary forms, with or without
examples/40_cutlass_py/customizable/gemm.py
+2 -2
View File
@@ -1,6 +1,6 @@
################################################################################
#
# Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
#
# Redistribution and use in source and binary forms, with or without
@@ -32,9 +32,9 @@
import numpy as np
import pycutlass
from pycutlass import *
from pycutlass.utils.device import device_cc
import cutlass
from bfloat16 import bfloat16
from pycutlass.utils.device import device_cc
import sys
import argparse
examples/40_cutlass_py/customizable/gemm_grouped.py
+1 -1
View File
@@ -1,6 +1,6 @@
################################################################################
#
# Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
#
# Redistribution and use in source and binary forms, with or without
examples/40_cutlass_py/gemm.py
+1 -2
View File
@@ -1,6 +1,6 @@
################################################################################
#
# Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
#
# Redistribution and use in source and binary forms, with or without
@@ -94,7 +94,6 @@ math_inst = MathInstruction(
MathOperation.multiply_add
)
tile_description = TileDescription(
[128, 128, 32], # Threadblock shape
2, # Number of stages
examples/40_cutlass_py/gemm_grouped.py
+1 -1
View File
@@ -1,6 +1,6 @@
################################################################################
#
# Copyright (c) 2017 - 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2017 - 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
#
# Redistribution and use in source and binary forms, with or without