CUDA 11.2u1 update

pawelszczerbuk · Feb 10, 2021 · 2b5ffa4 · 2b5ffa4
1 parent 86d05e4
commit 2b5ffa4
Show file tree

Hide file tree

Showing 79 changed files with 1,270 additions and 63 deletions.
diff --git a/cuSPARSE/Makefile b/cuSPARSE/Makefile
@@ -0,0 +1,108 @@
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
+#
+# NOTICE TO LICENSEE:
+#
+# This source code and/or documentation ("Licensed Deliverables") are
+# subject to NVIDIA intellectual property rights under U.S. and
+# international Copyright laws.
+#
+# These Licensed Deliverables contained herein is PROPRIETARY and
+# CONFIDENTIAL to NVIDIA and is being provided under the terms and
+# conditions of a form of NVIDIA software license agreement by and
+# between NVIDIA and Licensee ("License Agreement") or electronically
+# accepted by Licensee.  Notwithstanding any terms or conditions to
+# the contrary in the License Agreement, reproduction or disclosure
+# of the Licensed Deliverables to any third party without the express
+# written consent of NVIDIA is prohibited.
+#
+# NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
+# LICENSE AGREEMENT, NVIDIA MAKES NO REPRESENTATION ABOUT THE
+# SUITABILITY OF THESE LICENSED DELIVERABLES FOR ANY PURPOSE.  IT IS
+# PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED WARRANTY OF ANY KIND.
+# NVIDIA DISCLAIMS ALL WARRANTIES WITH REGARD TO THESE LICENSED
+# DELIVERABLES, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY,
+# NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
+# NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
+# LICENSE AGREEMENT, IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY
+# SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, OR ANY
+# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+# OF THESE LICENSED DELIVERABLES.
+#
+# U.S. Government End Users.  These Licensed Deliverables are a
+# "commercial item" as that term is defined at 48 C.F.R. 2.101 (OCT
+# 1995), consisting of "commercial computer software" and "commercial
+# computer software documentation" as such terms are used in 48
+# C.F.R. 12.212 (SEPT 1995) and is provided to the U.S. Government
+# only as a commercial end item.  Consistent with 48 C.F.R.12.212 and
+# 48 C.F.R. 227.7202-1 through 227.7202-4 (JUNE 1995), all
+# U.S. Government End Users acquire the Licensed Deliverables with
+# only those rights set forth herein.
+#
+# Any use of the Licensed Deliverables in individual and commercial
+# software must include, in the user documentation and internal
+# comments to the code, the above Disclaimer and U.S. Government End
+# Users Notice.
+
+FLAGS=INC=-I$(GPGPU)/cusparse/branches/dev/include\                            \
+          -I$(GPGPU)/cuda/tools/cudart\                                        \
+          -I$(GPGPU)/bin/x86_64_Linux_release\                                 \
+          -I$(GPGPU)/bin/x86_64_Linux_release\include
+
+all:
+	make -C spvv            $(FLAGS)
+	make -C axpby	        $(FLAGS)
+	make -C gather          $(FLAGS)
+	make -C rot             $(FLAGS)
+	make -C scatter         $(FLAGS)
+	make -C sparse2dense    $(FLAGS)
+	make -C dense2sparse    $(FLAGS)
+	make -C spmv_csr        $(FLAGS)
+	make -C spmv_coo        $(FLAGS)
+	make -C spsv_csr        $(FLAGS)
+	make -C spmm_csr        $(FLAGS)
+	make -C spmm_coo        $(FLAGS)
+	make -C spmm_blockedell $(FLAGS)
+	make -C sddmm_csr       $(FLAGS)
+	make -C spgemm          $(FLAGS)
+	make -C compression     $(FLAGS)
+	make -C graph_capture   $(FLAGS)
+
+clean:
+	rm -f spvv/spvv_example                                                    \
+          axpby/axpby_example                                                  \
+          gather/gather_example                                                \
+          rot/rot_example                                                      \
+          scatter/scatter_example                                              \
+          sparse2dense/sparse2dense_example                                    \
+          dense2sparse/dense2sparse_example                                    \
+          spmv_csr/spmv_csr_example                                            \
+          spmv_coo/spmv_coo_example                                            \
+          spsv_csr/spsv_csr_example                                            \
+          spmm_csr/spmm_csr_example                                            \
+          spmm_coo/spmm_coo_example                                            \
+          spmm_blockedell/spmm_blockedell_example                              \
+          sddmm_csr/sddmm_csr_example                                          \
+          spgemm/spgemm_example                                                \
+          compression/compression_example                                      \
+          graph_capture/graph_capture_example
+
+test:
+	spvv/spvv_example
+	axpby/axpby_example
+	gather/gather_example
+	rot/rot_example
+	scatter/scatter_example
+	sparse2dense/sparse2dense_example
+	dense2sparse/dense2sparse_example
+	spmv_csr/spmv_csr_example
+	spmv_coo/spmv_coo_example
+	spsv_csr/spsv_csr_example
+	spmm_csr/spmm_csr_example
+	spmm_coo/spmm_coo_example
+	spmm_blockedell/spmm_blockedell_example
+	sddmm_csr/sddmm_csr_example
+	spgemm/spgemm_example
+	compression/compression_example
+	graph_capture/graph_capture_example
diff --git a/cuSPARSE/README.md b/cuSPARSE/README.md
@@ -44,15 +44,23 @@ This folder demonstrates cuSPARSE Generic APIs usage.
 
 * [cusparseSpMM CSR](spmm_csr/)
 
-    The sample demonstrates *sparse matrix - dense matrix multiplication*, where the sparse matrix is represented in CSR (Compressed Sparse Row) storage format
+    The sample demonstrates *sparse matrix - dense matrix multiplication = dense matrix*, where the sparse matrix is represented in CSR (Compressed Sparse Row) storage format
 
 * [cusparseSpMM COO](spmm_coo/)
 
-    The sample demonstrates *sparse matrix - dense matrix multiplication*, where the sparse matrix is represented in COO (Coordinate) storage format
+    The sample demonstrates *sparse matrix - dense matrix multiplication = dense matrix*, where the sparse matrix is represented in COO (Coordinate) storage format
+
+* [cusparseSpMM SDDMM](sddmm_csr/)
+
+    The sample demonstrates *dense matrix - dense matrix multiplication = sparse matrix*, where the sparse matrix is represented in CSR (Compressed Sparse Row) storage format
+
+* [cusparseSpMM Blocked-ELL](spmm_blockedell/)
+
+    The sample demonstrates *sparse matrix - dense matrix multiplication = dense matrix*, where the sparse matrix is represented in Blocked-ELL storage format
 
 * [cusparseSpGEMM](spgemm/)
 
-    The sample demonstrates *sparse matrix - sparse matrix multiplication*, where all operands are sparse matrices represented in CSR (Compressed Sparse Row) storage format
+    The sample demonstrates *sparse matrix - sparse matrix multiplication = sparse matrix*, where all operands are sparse matrices represented in CSR (Compressed Sparse Row) storage format
 
 ##### Conversion
 
@@ -68,8 +76,8 @@ This folder demonstrates cuSPARSE Generic APIs usage.
 
 * [CUDA Graph Capture](graph_capture/)
 
-    The sample demonstrates how to optimize *sparse vector - dense vector dot product* (`cusparseSpVV`) by exploting *CUDA Graph Capture functionality*
+    The sample demonstrates how to optimize *sparse vector - dense vector dot product* (`cusparseSpVV`) by exploiting *CUDA Graph Capture functionality*
 
 * [Hardware Memory Compression](compression/)
 
-    The sample demonstrates how to optimize *sparse vector - dense vector scaling and sum* (`cusparseAxpby`) by exploting NVIDIA Ampere architecture *Hardware Memory Compression*
+    The sample demonstrates how to optimize *sparse vector - dense vector scaling and sum* (`cusparseAxpby`) by exploiting NVIDIA Ampere architecture *Hardware Memory Compression*
diff --git a/cuSPARSE/axpby/CMakeLists.txt b/cuSPARSE/axpby/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/axpby/Makefile b/cuSPARSE/axpby/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/axpby/README.md b/cuSPARSE/axpby/README.md
@@ -34,7 +34,7 @@ This sample demonstrates the usage of `cusparseAxpby` for performing *sparse vec
 * **Supported SM Architectures:** SM 3.5, SM 3.7, SM 5.0, SM 5.2, SM 5.3, SM 6.0, SM 6.1, SM 6.2, SM 7.0, SM 7.2, SM 7.5, SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C99`
 
 ## Prerequisites

diff --git a/cuSPARSE/axpby/axpby.svg b/cuSPARSE/axpby/axpby.svg
diff --git a/cuSPARSE/axpby/axpby_example.c b/cuSPARSE/axpby/axpby_example.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *

diff --git a/cuSPARSE/compression/CMakeLists.txt b/cuSPARSE/compression/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/compression/Makefile b/cuSPARSE/compression/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/compression/README.md b/cuSPARSE/compression/README.md
@@ -2,7 +2,7 @@
 
 ## Description
 
-The sample demonstrates how to optimize *sparse vector - dense vector scaling and sum* (`cusparseAxpby`) by exploting NVIDIA Ampere architecture *Hardware Memory Compression*
+The sample demonstrates how to optimize *sparse vector - dense vector scaling and sum* (`cusparseAxpby`) by exploiting NVIDIA Ampere architecture *Hardware Memory Compression*
 
 [cuSPARSE Optimization Notes](https://docs.nvidia.com/cuda/cusparse/index.html#optimization-notes)
 
@@ -33,7 +33,7 @@ nv-nsight-cu-cli --metrics lts__gcomp_input_sectors_compression_achieved_algo_sd
 * **Supported SM Architectures:** SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C++14`
 
 ## Prerequisites

diff --git a/cuSPARSE/compression/compression_example.cpp b/cuSPARSE/compression/compression_example.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *

diff --git a/cuSPARSE/dense2sparse/CMakeLists.txt b/cuSPARSE/dense2sparse/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/dense2sparse/Makefile b/cuSPARSE/dense2sparse/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/dense2sparse/README.md b/cuSPARSE/dense2sparse/README.md
@@ -34,7 +34,7 @@ This sample demonstrates the usage of `cusparseDenseToSparse` for performing *de
 * **Supported SM Architectures:** SM 3.5, SM 3.7, SM 5.0, SM 5.2, SM 5.3, SM 6.0, SM 6.1, SM 6.2, SM 7.0, SM 7.2, SM 7.5, SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C99`
 
 ## Prerequisites

diff --git a/cuSPARSE/dense2sparse/dense2sparse_example.c b/cuSPARSE/dense2sparse/dense2sparse_example.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *

diff --git a/cuSPARSE/gather/CMakeLists.txt b/cuSPARSE/gather/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/gather/Makefile b/cuSPARSE/gather/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/gather/README.md b/cuSPARSE/gather/README.md
@@ -32,7 +32,7 @@ This sample demonstrates the usage of `cusparseGather` for performing *sparse ve
 * **Supported SM Architectures:** SM 3.5, SM 3.7, SM 5.0, SM 5.2, SM 5.3, SM 6.0, SM 6.1, SM 6.2, SM 7.0, SM 7.2, SM 7.5, SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C99`
 
 ## Prerequisites

diff --git a/cuSPARSE/gather/gather.svg b/cuSPARSE/gather/gather.svg
diff --git a/cuSPARSE/gather/gather_example.c b/cuSPARSE/gather/gather_example.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *

diff --git a/cuSPARSE/graph_capture/CMakeLists.txt b/cuSPARSE/graph_capture/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/graph_capture/Makefile b/cuSPARSE/graph_capture/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/graph_capture/README.md b/cuSPARSE/graph_capture/README.md
@@ -2,7 +2,7 @@
 
 ## Description
 
-The sample demonstrates how to optimize *sparse vector - dense vector dot product* (`cusparseSpVV`) by exploting *CUDA Graph Capture functionality*
+The sample demonstrates how to optimize *sparse vector - dense vector dot product* (`cusparseSpVV`) by exploiting *CUDA Graph Capture functionality*
 
 [cuSPARSE Optimization Notes](https://docs.nvidia.com/cuda/cusparse/index.html#optimization-notes)
 
@@ -27,7 +27,7 @@ The sample demonstrates how to optimize *sparse vector - dense vector dot produc
 * **Supported SM Architectures:** SM 3.5, SM 3.7, SM 5.0, SM 5.2, SM 5.3, SM 6.0, SM 6.1, SM 6.2, SM 7.0, SM 7.2, SM 7.5, SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C99`
 
 ## Prerequisites

diff --git a/cuSPARSE/graph_capture/graph_capture_example.c b/cuSPARSE/graph_capture/graph_capture_example.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *

diff --git a/cuSPARSE/rot/CMakeLists.txt b/cuSPARSE/rot/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/rot/Makefile b/cuSPARSE/rot/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/rot/README.md b/cuSPARSE/rot/README.md
@@ -32,7 +32,7 @@ This sample demonstrates the usage of `cusparseRot` for performing *Givens rotat
 * **Supported SM Architectures:** SM 3.5, SM 3.7, SM 5.0, SM 5.2, SM 5.3, SM 6.0, SM 6.1, SM 6.2, SM 7.0, SM 7.2, SM 7.5, SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C99`
 
 ## Prerequisites

diff --git a/cuSPARSE/rot/rot.svg b/cuSPARSE/rot/rot.svg
diff --git a/cuSPARSE/rot/rot_example.c b/cuSPARSE/rot/rot_example.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *

diff --git a/cuSPARSE/scatter/CMakeLists.txt b/cuSPARSE/scatter/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/scatter/Makefile b/cuSPARSE/scatter/Makefile
@@ -1,4 +1,4 @@
-# Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+# Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
 #
 # NOTICE TO LICENSEE:
 #

diff --git a/cuSPARSE/scatter/README.md b/cuSPARSE/scatter/README.md
@@ -32,7 +32,7 @@ This sample demonstrates the usage of `cusparseScatter` for performing *sparse v
 * **Supported SM Architectures:** SM 3.5, SM 3.7, SM 5.0, SM 5.2, SM 5.3, SM 6.0, SM 6.1, SM 6.2, SM 7.0, SM 7.2, SM 7.5, SM 8.0, SM 8.6
 * **Supported OSes:** Linux, Windows, QNX, Android
 * **Supported CPU Architectures**: x86_64, ppc64le, arm64
-* **Supported Compilers**: gcc, clang, icc, xlc, msvc, pgi
+* **Supported Compilers**: gcc, clang, Intel icc, IBM xlc, Microsoft msvc, Nvidia HPC SDK nvc
 * **Language**: `C99`
 
 ## Prerequisites

diff --git a/cuSPARSE/scatter/scatter.svg b/cuSPARSE/scatter/scatter.svg
diff --git a/cuSPARSE/scatter/scatter_example.c b/cuSPARSE/scatter/scatter_example.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 1993-2020 NVIDIA Corporation.  All rights reserved.
+ * Copyright 1993-2021 NVIDIA Corporation.  All rights reserved.
  *
  * NOTICE TO LICENSEE:
  *