|
Hello,
I work on the pkg Pyfai , I am in an internship at Synchrotron-Soleil , my directors are Frederic-
Emmanuel PICCA and Emmanuel FARHI. I implemented Rocm and Pocl autopkgtest for architecture amd64 and arm64. I implemented autopktests for rocm and pocl using Opencl on the package named Pyfai on local. The aim is to have an overview of code compatibility with various AMD graphics cards, the codes on all the AMD boards available for CI rocm for GPU and Pocl for CPU.
But I have several problems with it, it makes very long times to build , so that some tests are marked as timed out whatever I do.
I implemented the time limit at 42 200 second . In the ROCm parts , I have the error "Maximum valid workgroup size 256 on device <pyopencl.Device 'gfx1034' on 'AMD Accelerated Parallel Processing' at 0xe90bf90> 0.0 1.871411379818157e-05 "
I don't know how to solve that and what it come from ... I made a lot of research and I don't really know how to solve it.
It seems to be material , to solve it we must have a GPU AMD marked as PRO , not a gaming graphic card.
Our config :
*******
Agent 2
*******
Name: gfx1034
Uuid: GPU-XX
Marketing Name: AMD Radeon RX 6400
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 1
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
L2: 1024(0x400) KB
L3: 16384(0x4000) KB
Chip ID: 29759(0x743f)
ASIC Revision: 0(0x0)
Cacheline Size: 128(0x80)
Max Clock Freq. (MHz): 2320
BDFID: 20224
Internal Node ID: 1
Compute Unit: 12
SIMDs per CU: 2
Shader Engines: 1
Shader Arrs. per Eng.: 2
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Features: KERNEL_DISPATCH
Fast F16 Operation: TRUE
Wavefront Size: 32(0x20)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 32(0x20)
Max Work-item Per CU: 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 129
SDMA engine uCode:: 34
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 4177920(0x3fc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED
Size: 4177920(0x3fc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 3
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx1034
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
FBarrier Max Size: 32
I added Rocm and Pocl tools in debian/tests/control :
# tests that must pass
Test-Command: no-opencl
Architecture: !amd64 !arm64 !armel !armhf !i386
Depends:
bitshuffle,
python3-all,
python3-pyfai,
python3-tk,
xauth,
xvfb,
python3-pyqt5.qtopengl,
python3-pyqt5,
libgl1-mesa-glx,
Features: test-name=no-opencl
Restrictions: allow-stderr, skip-not-installable
Test-Command: rocm-test-launcher debian/tests/opencl
Architecture: amd64 arm64 armel armhf i386
Depends:
bitshuffle,
clinfo,
rocminfo,
libnuma1,
ocl-icd-libopencl1,
rocm-opencl-icd,
pkg-rocm-tools,
python3-all,
python3-pyfai,
python3-tk,
xauth,
xvfb,
libclang-common-17-dev,
hipcc,
rocm-device-libs-17,
Features: test-name=opencl-rocm
Restrictions: allow-stderr, skip-not-installable, skippable
Test-Command: debian/tests/opencl
Architecture: amd64 arm64 armel armhf i386
Depends:
bitshuffle,
pocl-opencl-icd,
clinfo,
python3-all,
python3-pyfai,
python3-tk,
xauth,
xvfb,
libclang-common-17-dev,
Features: test-name=opencl-pocl
Restrictions: allow-stderr, skip-not-installable
Test-Command: xvfb-run -s "-screen 0 1024x768x24 -ac +extension GLX +render -noreset" sh debian/tests/gui
Depends:
debhelper,
mesa-utils,
@,
xauth,
xvfb,
Restrictions: allow-stderr
And the file : debian/tests/opencl :
#!/bin/sh -e
# Check that OpenCL isn't totally broken (note that it isn't totally working either)
# Uses device 0 platform 0, i.e. to use a real GPU manually install its opencl-icd before running this
# Mark the test has flaky, the important part is the CPU computation.
export PYFAI_OPENCL=True
export PYOPENCL_COMPILER_OUTPUT=1
# skip test
# TestAzimHalfFrelon.test_medfilt1d
cp bootstrap.py run_tests.py pyproject.toml version.py README.rst "$AUTOPKGTEST_TMP"
for py in $(py3versions -s 2>/dev/null)
do cd "$AUTOPKGTEST_TMP"
echo "Testing with $py:"
xvfb-run -a --server-args="-screen 0 1024x768x24" $py run_tests.py -v -m --low-mem --installed
done
The error log for ROCm part:
When the autopkgtest for rocm is launched, I get this error at the end. Where does this come from?
INFO:memProf:Time: 60.074s RAM: 0.000 Mb pyFAI.test.test_containers.TestContainer.test_rebin1d ====================================================================== FAIL: testPyfaiBenchmark (pyFAI.test.test_scripts.TestScriptsHelp.testPyfaiBenchmark) ----------------------------------------------------------------------
Traceback (most recent call last): File "/usr/lib/python3/dist-packages/pyFAI/test/test_scripts.py", line 105, in testPyfaiBenchmark self.executeAppHelp("pyFAI-benchmark", "pyFAI.app.benchmark") ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3/dist-packages/pyFAI/test/test_scripts.py", line 86, in executeAppHelp self.executeCommandLine(command_line, env) ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3/dist-packages/pyFAI/test/test_scripts.py", line 79, in
executeCommandLine self.assertEqual(p.returncode, 0) ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ AssertionError: 1 != 0 ---------------------------------------------------------------------- Ran 453 tests in 5584.067s FAILED (failures=1, skipped=95) Maximum valid workgroup
size 256 on device <pyopencl.Device 'gfx1034' on 'AMD Accelerated Parallel Processing' at 0xe90bf90> 0.0 1.871411379818157e-05 autopkgtest [18:23:38]: test opencl-rocm: -----------------------] autopkgtest [18:23:38]: test opencl-rocm: - - - - - - - - - -
results - - - - - - - - - - opencl-rocm FAIL non-zero exit status 1
Thank you very much
Clément LONGEAC
|