Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

JNI Bindings to fetch CUDA compute capability versions. #10568

Merged
merged 2 commits into from
Apr 1, 2022
Merged

JNI Bindings to fetch CUDA compute capability versions. #10568

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dfd9975
JNI Bindings to fetch CUDA compute capability versions.
mythrocks Apr 1, 2022
c5fe1a2
Review comments:
mythrocks Apr 1, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 37 additions & 1 deletion java/src/main/java/ai/rapids/cudf/Cuda.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2019-2021, NVIDIA CORPORATION.
* Copyright (c) 2019-2022, NVIDIA CORPORATION.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
Expand Down Expand Up @@ -386,6 +386,42 @@ static void asyncMemcpy(long dst, long src, long count, CudaMemcpyKind kind) {
*/
static native int getNativeComputeMode() throws CudaException;

/**
* Gets the major CUDA compute capability of the current device.
*
* For reference: https://developer.nvidia.com/cuda-gpus
* Hardware Generation Compute Capability
* Ampere 8.x
* Turing 7.5
* Volta 7.0, 7.2
* Pascal 6.x
* Maxwell 5.x
* Kepler 3.x
* Fermi 2.x
*
* @return The Major compute capability version number of the current CUDA device
* @throws CudaException on any error
*/
public static native int getComputeCapabilityMajor() throws CudaException;

/**
* Gets the minor CUDA compute capability of the current device.
*
* For reference: https://developer.nvidia.com/cuda-gpus
* Hardware Generation Compute Capability
* Ampere 8.x
* Turing 7.5
* Volta 7.0, 7.2
* Pascal 6.x
* Maxwell 5.x
* Kepler 3.x
* Fermi 2.x
*
* @return The Minor compute capability version number of the current CUDA device
* @throws CudaException on any error
*/
public static native int getComputeCapabilityMinor() throws CudaException;

/**
* Calls cudaFree(0). This can be used to initialize the GPU after a setDevice()
* @throws CudaException on any error
Expand Down
30 changes: 29 additions & 1 deletion java/src/main/native/src/CudaJni.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
* Copyright (c) 2019-2021, NVIDIA CORPORATION.
* Copyright (c) 2019-2022, NVIDIA CORPORATION.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
Expand Down Expand Up @@ -195,6 +195,34 @@ JNIEXPORT jint JNICALL Java_ai_rapids_cudf_Cuda_getNativeComputeMode(JNIEnv *env
CATCH_STD(env, -2);
}

JNIEXPORT jint JNICALL Java_ai_rapids_cudf_Cuda_getComputeCapabilityMajor(JNIEnv *env, jclass) {
try {
cudf::jni::auto_set_device(env);
int device;
JNI_CUDA_TRY(env, -2, ::cudaGetDevice(&device));
mythrocks marked this conversation as resolved.
Show resolved Hide resolved
int attribute_value;
JNI_CUDA_TRY(
env, -2,
::cudaDeviceGetAttribute(&attribute_value, ::cudaDevAttrComputeCapabilityMajor, device));
return attribute_value;
}
CATCH_STD(env, -2);
}

JNIEXPORT jint JNICALL Java_ai_rapids_cudf_Cuda_getComputeCapabilityMinor(JNIEnv *env, jclass) {
try {
cudf::jni::auto_set_device(env);
int device;
JNI_CUDA_TRY(env, -2, ::cudaGetDevice(&device));
int attribute_value;
JNI_CUDA_TRY(
env, -2,
::cudaDeviceGetAttribute(&attribute_value, ::cudaDevAttrComputeCapabilityMinor, device));
return attribute_value;
}
CATCH_STD(env, -2);
}

JNIEXPORT void JNICALL Java_ai_rapids_cudf_Cuda_freeZero(JNIEnv *env, jclass) {
try {
cudf::jni::auto_set_device(env);
Expand Down