PyCUDA June 2014

pycuda@tiker.net

6 participants
7 discussions

by Tomasz Rybak

Hello. I've been packaging PyCUDA for Debian. I run all the tests to ensure that package works on Python 2 and Python 3. All tests pass except for on from test_driver.py: $ python test_driver.py ============================= test session starts ============================== platform linux2 -- Python 2.7.5 -- pytest-2.3.5 collected 21 items test_driver.py ........F............ =================================== FAILURES =================================== _____________________ TestDriver.test_register_host_memory _____________________ args = (<test_driver.TestDriver instance at 0x24e7d88>,), kwargs = {} pycuda = <module 'pycuda' from '/usr/lib/python2.7/dist-packages/pycuda/__init__.pyc'> ctx = <pycuda._driver.Context object at 0x2504488> clear_context_caches = <function clear_context_caches at 0x1dbf848> collect = <built-in function collect> def f(*args, **kwargs): import pycuda.driver # appears to be idempotent, i.e. no harm in calling it more than once pycuda.driver.init() ctx = make_default_context() try: assert isinstance(ctx.get_device().name(), str) assert isinstance(ctx.get_device().compute_capability(), tuple) assert isinstance(ctx.get_device().get_attributes(), dict) > inner_f(*args, **kwargs) /usr/lib/python2.7/dist-packages/pycuda/tools.py:434: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <test_driver.TestDriver instance at 0x24e7d88> @mark_cuda_test def test_register_host_memory(self): if drv.get_version() < (4,): from py.test import skip skip("register_host_memory only exists on CUDA 4.0 and later") import sys if sys.platform == "darwin": from py.test import skip skip("register_host_memory is not supported on OS X") a = drv.aligned_empty((2**20,), np.float64, alignment=4096) > drv.register_host_memory(a) E LogicError: cuMemHostRegister failed: invalid value test_driver.py:559: LogicError ==================== 1 failed, 20 passed in 116.85 seconds ===================== This test fails both on ION (GeForce 9400M, CC 1.1) and GeForce 460 (CC 2.1). I've compiled PyCUDA with gcc 4.8, run with kernel 3.9 and drivers 304.88. Regards. -- Tomasz Rybak GPG/PGP key ID: 2AD5 9860 Fingerprint A481 824E 7DD3 9C0E C40A 488E C654 FB33 2AD5 9860 http://member.acm.org/~tomaszrybak

6 years, 8 months

Weird bug when slicing arrays on Kepler cards

by Thomas Unterthiner

Hi there! I am currently chasing a very weird bug in my code: The following code will consistently crash on Kepler-type GPUs (tested on a Tesla K40 and on a GTX 780), but runs fine on my Fermi-class notebook GPU: import numpy as np import pycuda.autoinit from pycuda import gpuarray from pycuda.driver import Stream from scikits.cuda.cublas import cublasSgemm import scikits.cuda.autoinit from scikits.cuda.misc import _global_cublas_handle as handle for _ in range(3): n = 131 s = slice(128, n) X = gpuarray.to_gpu(np.random.randn(n, 2483).astype(np.float32)) a = gpuarray.empty((X.shape[1], 3), dtype=np.float32) c = gpuarray.empty((a.shape[0], X.shape[1]), dtype=np.float32) b = gpuarray.empty_like(X) m, n, k = a.shape[0], b[s].shape[1], a.shape[1] lda, ldb, ldc = m, k, m cublasSgemm(handle, 'n', 'n', m, n, k, 1.0, b[s].gpudata, lda, a.gpudata, ldb, 0.0, c.gpudata, ldc) stream = Stream() stream.synchronize() The errors I'm getting are: Traceback (most recent call last): File "<stdin>", line 22, in <module> pycuda._driver.LogicError: cuStreamSynchronize failed: invalid/unknown error code >>> PyCUDA WARNING: a clean-up operation failed (dead context maybe?) cuStreamDestroy failed: invalid/unknown error code PyCUDA WARNING: a clean-up operation failed (dead context maybe?) cuMemFree failed: invalid/unknown error code PyCUDA WARNING: a clean-up operation failed (dead context maybe?) cuMemFree failed: invalid/unknown error code PyCUDA WARNING: a clean-up operation failed (dead context maybe?) cuMemFree failed: invalid/unknown error code PyCUDA WARNING: a clean-up operation failed (dead context maybe?) cuMemFree failed: invalid/unknown error code the Stream - thing at the end of the code is only necessary to notice the error (by triggering error-checks). Copies to/from the device would also trigger the same errors. The bug is extremely weird, especially since: * the used constants seem to matter. If I change 'n' to 132 the error goes away. If I change the 2nd dimension of X to 100 instead of 2483, it goes away as well. * the order of the allocations matter. If I allocate 'd' before 'c', the error goes away * the for-loop is necessary (i.e., the error only occurs at the third run-through) Still, the error seems to be completely reproducable across different machines (tried on a machine running CentOS 6 on a K40, on a machine running Ubuntu 13.10 on a K40 and on a machine running Xubuntu 14.04 on a GTX 780). At this point, I am at a complete loss. I don't know if the error is caused by PyCUDA, cuBLAS or scikits.cuda (the latter seems the least probable since cublasSgemm is very straight-forward) or by something else entirely. I'd appreciate any help or advice. Cheers Thomas

6 years, 9 months

Re: [PyCUDA] SCHED_BLOCKING_SYNC query

by Andreas Kloeckner

Dear Junyi, Junyi <9jhzguy(a)gmail.com> writes: > For the duration of the kernel call, the cpu busy-waits by default. I > changed the make_context() portion to include the SCHED_BLOCKING_SYNC flag, > but the kernel call just hangs. How should I trigger the release? Thanks! Can you please supply a) a reproducing snippet of code (ideally short) and b) some information about your system (GPU, OS, CUDA, Python versions)? Thanks! Andreas

6 years, 9 months

Development environment

by Daniel

Hi All, I just installed PyCuda and got it working on my Windows 8.1 laptop. I'm able to run the examples in VS 2010. My question concerns the 'preferred' development environment for PyCuda: While it runs on Windows, I'm not able to debug any kernel code using VS (Nvidia's Nsight) like I can using C/C++. I've seen a bunch of threads concerning 'cuda-gdb' which leads me to believe folks are using the command line on Linux to run PyCuda. Is this the 'preferred' environment to run/debug PyCuda? Is there a way to debug the kernels in PyCuda in Windows with/without VS Nsight or are we forced to use a command line interface for debugging purposes? Thanks, Daniel

6 years, 9 months

SCHED_BLOCKING_SYNC query

by Junyi

For the duration of the kernel call, the cpu busy-waits by default. I changed the make_context() portion to include the SCHED_BLOCKING_SYNC flag, but the kernel call just hangs. How should I trigger the release? Thanks! Jimmy

6 years, 9 months

Re: [PyCUDA] build/install error - internal compiler error?

by Andreas Kloeckner

JeHoon Song <song.je-hoon(a)kaist.ac.kr> writes: > Hello, > > I just started to develop PyCUDA application. > > It build process is not successful as following: > > ... > bpl-subset/bpl_subset/boost/type_traits/detail/cv_traits_impl.hpp:37: > internal compiler error: in make_rtl_for_nonlocal_decl, at cp/decl.c:5067 > ... http://wiki.tiker.net/PyCuda/FrequentlyAskedQuestions#I_have_.3Cinsert_rand… HTH, Andreas

6 years, 9 months

build/install error - internal compiler error?

by JeHoon Song

Hello, I just started to develop PyCUDA application. It build process is not successful as following: ... bpl-subset/bpl_subset/boost/type_traits/detail/cv_traits_impl.hpp:37: internal compiler error: in make_rtl_for_nonlocal_decl, at cp/decl.c:5067 ... I am not sure if I have to upgrade gcc. My gcc version is as following: (j277)[pbs@tesla0 pycuda]$ gcc -v Using built-in specs. Target: x86_64-redhat-linux Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-libgcj-multifile --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --enable-plugin --with-java-home=/usr/lib/jvm/java-1.4.2-gcj-1.4.2.0/jre --with-cpu=generic --host=x86_64-redhat-linux Thread model: posix gcc version 4.1.2 20080704 (Red Hat 4.1.2-44) Could you help me to fix this problem? Best, Je-Hoon Song -- *Je-Hoon Song* Ph.D. Candidate Laboratory for Systems Biology and Bio-Inspired Engineering (SBIE), Department of Bio and Brain Engineering, KAIST, Republic of Korea Phone: +82-42-350-4365

6 years, 9 months

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

PyCUDA June 2014