Opencl platform and device selection #67
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
glupescu
force-pushed
the
opencl-update
branch
6 times, most recently
from
d79fbb6
to
dc5abce
Compare
sakridge
reviewed
May 6, 2020
src/Makefile
Outdated
| @@ -21,22 +21,35 @@ CL_LIB=cl-crypt | |||
|
|
|||
| CHACHA_IF_DIR:=crypt-if | |||
|
|
|||
| CL_HEADER_DIR:=opencl-platform | |||
| # for Windows NVIDIA cygwin sample | |||
There was a problem hiding this comment.
Remove commented lines or do some kind of platform detection.
There was a problem hiding this comment.
Just wanted to give some examples, but maybe these would be better placed in the Readme ?
sakridge
reviewed
May 6, 2020
src/Makefile
Outdated
|
|
||
| # some instances require optimisations disabled (e.g. AMD on Linux) | ||
| # remove "-cl-opt-disable" for default Optimisations to take place | ||
| CL_DEVICE_CFLAGS=-cl-opt-disable |
There was a problem hiding this comment.
ok; probably should be runtime detected
There was a problem hiding this comment.
In the sense of available as environment variable ?
The problem is not so much about detection, but about policy - what to apply on specific platform.
Maybe also get platform and number to environment variables ?
sakridge
reviewed
May 6, 2020
src/Makefile
Outdated
|
|
||
| $V/cl_ecc_main.o: $(CL_ECC_DIR)/main.cpp $(ECC_DIR)/ed25519.h | ||
| @mkdir -p $(@D) | ||
| $(CXX) $(CL_CFLAGS) -pthread -I$(ECC_DIR) -c $< -o $@ | ||
|
|
||
| $V/$(CL_ECC_TEST_BIN): $V/cl_ecc_main.o $V/lib$(CL_LIB).so | ||
| $V/$(CL_ECC_TEST_BIN): $V/cl_ecc_main.o $V/lib$(CL_LIB).a |
glupescu
force-pushed
the
opencl-update
branch
from
dc5abce
to
9b33e61
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This set of changes introduces a way to select the platform and device for OpenCL and is used for the binary cl_ed25519_verify
Usage example:
src/debug/cl_ed25519_verify.exe -h
usage: src/debug/cl_ed25519_verify [-v] <num_signatures> <num_elems> <num_sigs_per_packet> <num_threads> <num_iterations> <use_non_default_stream> <cl_platform_id> <cl_device_id>
$ ./cl_ed25519_verify 100000 1 1 1 1 1 1 2
OpenCL platform query & init...
OpenCL init devices query type: ALL
Platforms found: 2
Platform 0 Intel(R) Corporation OpenCL 1.2 LINUX
Devices found 1
Device 0 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
Platform 1 NVIDIA Corporation OpenCL 1.2 CUDA 9.1.84
Devices found 3
Device 0 Tesla K40m
Device 1 Tesla K40m
Device 2 Tesla K40m <----- SELECTED
Compiling sha256 kernels
Compiling verify kernels
time diff: 157882.000000 total: 100000 signs/sec: 633384.426344
time diff: 1380897.000000 total: 100000 verifies/sec: 72416.697263
$ ./cl_ed25519_verify.exe 10000 1 1 1 1 1 1 0
OpenCL platform query & init...
OpenCL init devices query type: ALL
Platforms found: 2
Platform 0 Intel(R) Corporation OpenCL 1.2
Devices found 1
Device 0 Intel(R) Core(TM) i3-3250 CPU @ 3.50GHz
Platform 1 Advanced Micro Devices, Inc. OpenCL 2.1 AMD-APP (3004.7)
Devices found 4
Device 0 Hawaii <----- SELECTED
Device 1 Hawaii
Device 2 Hawaii
Device 3 Fiji
Compiling sha256 kernels
Compiling verify kernels
time diff: 55538.000000 total: 10000 signs/sec: 180056.897980
time diff: 23255.000000 total: 10000 verifies/sec: 430015.050527
$ ./cl_ed25519_verify 1 1 1 1 1 1 0 0
OpenCL platform query & init...
OpenCL init devices query type: ALL
Platforms found: 2
Platform 0 Intel(R) Corporation OpenCL 1.2 LINUX
Devices found 1
Device 0 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz <----- SELECTED
Platform 1 NVIDIA Corporation OpenCL 1.2 CUDA 9.1.84
Devices found 3
Device 0 Tesla K40m
Device 1 Tesla K40m
Device 2 Tesla K40m
Compiling sha256 kernels
Compiling verify kernels
8 warnings generated.
time diff: 4297.000000 total: 1 signs/sec: 232.720503
time diff: 1835.000000 total: 1 verifies/sec: 544.959128