mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-13 00:08:26 +08:00
CUDA 13.2 samples update (#432)
- Added Python samples for CUDA Python 1.0 release - Renamed top-level `Samples` directory to `cpp` to accommodate Python samples.
This commit is contained in:
Dheemanth
GitHub
57
cpp/7_libNVVM/cuda-shared-memory/CMakeLists.txt
Normal file
57
cpp/7_libNVVM/cuda-shared-memory/CMakeLists.txt
Normal file
@@ -0,0 +1,57 @@
|
||||
# Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions
|
||||
# are met:
|
||||
# * Redistributions of source code must retain the above copyright
|
||||
# notice, this list of conditions and the following disclaimer.
|
||||
# * Redistributions in binary form must reproduce the above copyright
|
||||
# notice, this list of conditions and the following disclaimer in the
|
||||
# documentation and/or other materials provided with the distribution.
|
||||
# * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
# contributors may be used to endorse or promote products derived
|
||||
# from this software without specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
add_custom_target(clobber)
|
||||
add_custom_target(testrun)
|
||||
|
||||
add_test(NAME test-cuda-shared-memory-shared_memory
|
||||
COMMAND "${CMAKE_CURRENT_BINARY_DIR}/../ptxgen/ptxgen" "${CMAKE_CURRENT_SOURCE_DIR}/shared_memory.ll"
|
||||
WORKING_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}")
|
||||
|
||||
add_test(NAME test-cuda-shared-memory-extern_shared_memory
|
||||
COMMAND "${CMAKE_CURRENT_BINARY_DIR}/../ptxgen/ptxgen" "${CMAKE_CURRENT_SOURCE_DIR}/extern_shared_memory.ll"
|
||||
WORKING_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}")
|
||||
|
||||
set_tests_properties(test-cuda-shared-memory-shared_memory
|
||||
test-cuda-shared-memory-extern_shared_memory
|
||||
PROPERTIES FIXTURES_REQUIRED PTXGENTEST)
|
||||
|
||||
# Install to CUDA_SAMPLES_INSTALL_DIR if defined (for unified installation),
|
||||
# otherwise install to bin/cuda-shared-memory (for standalone libNVVM build)
|
||||
if(DEFINED CUDA_SAMPLES_INSTALL_DIR)
|
||||
install(FILES shared_memory.ll DESTINATION ${CUDA_SAMPLES_INSTALL_DIR}/cuda-shared-memory)
|
||||
install(FILES extern_shared_memory.ll DESTINATION ${CUDA_SAMPLES_INSTALL_DIR}/cuda-shared-memory)
|
||||
else()
|
||||
install(FILES shared_memory.ll DESTINATION bin/cuda-shared-memory)
|
||||
install(FILES extern_shared_memory.ll DESTINATION bin/cuda-shared-memory)
|
||||
endif()
|
||||
|
||||
file(COPY shared_memory.ll DESTINATION "${CMAKE_CURRENT_BINARY_DIR}")
|
||||
file(COPY extern_shared_memory.ll DESTINATION "${CMAKE_CURRENT_BINARY_DIR}")
|
||||
|
||||
# Copy the .ll files to the folder of executable file for full testing
|
||||
file(COPY shared_memory.ll DESTINATION ${CMAKE_CURRENT_BINARY_DIR}/../ptxgen/cuda-shared-memory)
|
||||
file(COPY extern_shared_memory.ll DESTINATION ${CMAKE_CURRENT_BINARY_DIR}/../ptxgen/cuda-shared-memory)
|
||||
58
cpp/7_libNVVM/cuda-shared-memory/extern_shared_memory.ll
Normal file
58
cpp/7_libNVVM/cuda-shared-memory/extern_shared_memory.ll
Normal file
@@ -0,0 +1,58 @@
|
||||
; Copyright (c) 2014-2023, NVIDIA CORPORATION. All rights reserved.
|
||||
;
|
||||
; Redistribution and use in source and binary forms, with or without
|
||||
; modification, are permitted provided that the following conditions
|
||||
; are met:
|
||||
; * Redistributions of source code must retain the above copyright
|
||||
; notice, this list of conditions and the following disclaimer.
|
||||
; * Redistributions in binary form must reproduce the above copyright
|
||||
; notice, this list of conditions and the following disclaimer in the
|
||||
; documentation and/or other materials provided with the distribution.
|
||||
; * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
; contributors may be used to endorse or promote products derived
|
||||
; from this software without specific prior written permission.
|
||||
;
|
||||
; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
; EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
; IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
; PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
; CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
; EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
; PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
; PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
; OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
; (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
; OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
; This NVVM IR program shows how to use unsize external shared memory.
|
||||
; What it does is similar to the following CUDA C code.
|
||||
;
|
||||
; extern __shared__ int a[];
|
||||
;
|
||||
; __global__ void foo()
|
||||
; {
|
||||
; int *p1 = a;
|
||||
; float *p2 = (float *)&a[10];
|
||||
;
|
||||
; *p1 = 10;
|
||||
; *p2 = 21.0f;
|
||||
; }
|
||||
;
|
||||
|
||||
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-i128:128:128-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
|
||||
target triple = "nvptx64-nvidia-cuda"
|
||||
|
||||
@a = external addrspace(3) global [0 x i32]
|
||||
|
||||
define void @foo() {
|
||||
entry:
|
||||
store i32 10, i32 addrspace(3)* getelementptr inbounds ([0 x i32], [0 x i32] addrspace(3)* @a, i64 0, i64 0), align 4
|
||||
store float 2.100000e+01, float addrspace(3)* bitcast (i32 addrspace(3)* getelementptr inbounds ([0 x i32], [0 x i32] addrspace(3)* @a, i64 0, i64 10) to float addrspace(3)*), align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
!nvvm.annotations = !{!0}
|
||||
!0 = !{void ()* @foo, !"kernel", i32 1}
|
||||
|
||||
!nvvmir.version = !{!1}
|
||||
!1 = !{i32 2, i32 0}
|
||||
58
cpp/7_libNVVM/cuda-shared-memory/shared_memory.ll
Normal file
58
cpp/7_libNVVM/cuda-shared-memory/shared_memory.ll
Normal file
@@ -0,0 +1,58 @@
|
||||
; Copyright (c) 2014-2023, NVIDIA CORPORATION. All rights reserved.
|
||||
;
|
||||
; Redistribution and use in source and binary forms, with or without
|
||||
; modification, are permitted provided that the following conditions
|
||||
; are met:
|
||||
; * Redistributions of source code must retain the above copyright
|
||||
; notice, this list of conditions and the following disclaimer.
|
||||
; * Redistributions in binary form must reproduce the above copyright
|
||||
; notice, this list of conditions and the following disclaimer in the
|
||||
; documentation and/or other materials provided with the distribution.
|
||||
; * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
; contributors may be used to endorse or promote products derived
|
||||
; from this software without specific prior written permission.
|
||||
;
|
||||
; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
; EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
; IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
; PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
; CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
; EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
; PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
; PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
; OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
; (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
; OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
; This NVVM IR program shows how to use shared memory.
|
||||
; What it does is similar to the following CUDA C code.
|
||||
;
|
||||
;
|
||||
; __shared__ int a;
|
||||
; __shared__ int b[10];
|
||||
;
|
||||
; __global__ void foo()
|
||||
; {
|
||||
; a = 1;
|
||||
; b[5] = 2;
|
||||
; }
|
||||
;
|
||||
|
||||
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-i128:128:128-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
|
||||
target triple = "nvptx64-nvidia-cuda"
|
||||
|
||||
@a = internal addrspace(3) global i32 undef, align 4
|
||||
@b = internal addrspace(3) global [10 x i32] undef, align 4
|
||||
|
||||
define void @foo() {
|
||||
entry:
|
||||
store i32 1, i32 addrspace(3)* @a, align 4
|
||||
store i32 2, i32 addrspace(3)* getelementptr inbounds ([10 x i32], [10 x i32] addrspace(3)* @b, i64 0, i64 5), align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
!nvvm.annotations = !{!0}
|
||||
!0 = !{void ()* @foo, !"kernel", i32 1}
|
||||
|
||||
!nvvmir.version = !{!1}
|
||||
!1 = !{i32 2, i32 0}
|
||||
Reference in New Issue
Block a user