Andreas Beckmann wrote:
I need more instructions to reproduce this ...
# apt-get install python3-pygpu python3-nose python3-scipy libclblas-dev
ocl-icd-opencl-dev pocl-opencl-icd
$ DEVICE=opencl0:0 python3 /usr/bin/nosetests3 -v pygpu.tests.test_blas
You may need to run the second one twice (if it gets to test_ger and
fails with "free(): invalid next size (normal)" or similar memory
corruption errors, that's a different bug, which I am currently
investigating), but do not need any source packages: the pygpu tests are
included in the binary.
please try pocl from experimental which is built against llvm-7
Doesn't fix it but possibly makes it rarer (the pygpu case now requires
running the test suite twice).
Using LLVM 7 also avoids #914021, allowing a backtrace:
$ DEVICE=opencl0:0 gdb --args python3 /usr/bin/nosetests3 -v
pygpu.tests.test_blas
(gdb) break lib/IR/Verifier.cpp:1397
No source file named lib/IR/Verifier.cpp.
Make breakpoint pending on future shared library load? (y or [n]) y
Breakpoint 1 (lib/IR/Verifier.cpp:1397) pending.
(gdb) bt full
#0 visitModuleFlag ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IR/Verifier.cpp:1398
No locals.
#1 visitModuleFlags ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IR/Verifier.cpp:1306
No locals.
#2 verify ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IR/Verifier.cpp:384
No locals.
#3 0x00007ffff0db15db in verifyModule ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IR/Verifier.cpp:4689
No locals.
#4 0x00007ffff0cbcf5d in UpgradeDebugInfo ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IR/AutoUpgrade.cpp:3521
No locals.
#5 0x00007ffff12c001f in materializeModule ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/Bitcode/Reader/BitcodeReader.cpp:4803
No locals.
#6 0x00007ffff0d890ea in materializeAll ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IR/Module.cpp:397
No locals.
#7 0x00007ffff12b806e in getModuleImpl ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/Bitcode/Reader/BitcodeReader.cpp:5769
No locals.
#8 0x00007ffff12bd562 in parseModule ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/Bitcode/Reader/BitcodeReader.cpp:5883
No locals.
#9 parseBitcodeFile ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/Bitcode/Reader/BitcodeReader.cpp:5894
No locals.
#10 0x00007ffff0ddb2cf in parseIR ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IRReader/IRReader.cpp:79
No locals.
#11 0x00007ffff0ddb693 in parseIRFile ()
at
/build/llvm-toolchain-7-Ael5Ob/llvm-toolchain-7-7.0.1/lib/IRReader/IRReader.cpp:108
No locals.
#12 0x00007ffff3f93f6b in parseModuleIR (
path=path@entry=0x7fffffff9360
"/home/test1/.cache/pocl/kcache/JG/ABBLKFOBNDALGEFMHDFBNNLBFBJABFEGHNMOO/program.bc")
at /usr/lib/llvm-7/include/llvm/ADT/StringRef.h:85
Err = {SM = 0x0, Loc = {Ptr = 0x0}, Filename = "", LineNo = 0,
ColumnNo = 0, Kind = llvm::SourceMgr::DK_Error, Message = "",
LineContents = "", Ranges = std::vector of length 0, capacity 0,
FixIts = {<llvm::SmallVectorImpl<llvm::SMFixIt>> =
{<llvm::SmallVectorTemplateBase<llvm::SMFixIt, false>> =
{<llvm::SmallVectorTemplateCommon<llvm::SMFixIt, void>> =
{<llvm::SmallVectorBase> = {BeginX = 0x7fffffff9268, Size = 0,
Capacity = 4}, <No data fields>}, <No data
fields>}, <No data fields>}, <llvm::SmallVectorStorage<llvm::SMFixIt,
4>> = {InlineElts = {
{<llvm::AlignedCharArray<8, 48>> = {
buffer =
"@\223\377\377\377\177\000\000\200\222\377\377\377\177\000\000\000\261\245\353\227\346\350\327\020\223\377\377\377\177\000\000\321\223T\366\377\177\000\000\020\000\000\000\000\000\000"},
<No data fields>},
{<llvm::AlignedCharArray<8, 48>> = {
buffer =
"\002\000\000\000\000\000\000\000\000\000\022@\000\000\022@\300\v(\365\377\177\000\000\060\222\377\377\377\177\000\000\000\261\245\353\227\346\350\327\340\370S\a\000\000\000"},
<No data fields>},
{<llvm::AlignedCharArray<8, 48>> = {
buffer =
"\260\226\377\377\377\177\000\000\002\000\000\000\000\000\000\000\360\276\352\000\000\000\000\000\320\206P\a\000\000\000\000\340\206P\a\000\000\000\000\260\225\377\377\377\177\000"},
<No data fields>},
{<llvm::AlignedCharArray<8, 48>> = {
buffer = "J\206W\366\377\177", '\000' <repeats 18
times>,
"`\223\377\377\377\177\000\000\353\375\365\363\377\177\000\000\001\000\000\000\000\000\000"},
<No data fields>}}}, <No data fields>}}
#13 0x00007ffff3f95d2d in pocl_update_program_llvm_irs_unlocked (
program=program@entry=0x750fe50, device_i=device_i@entry=0)
at ./lib/CL/pocl_llvm_wg.cc:516
program_bc_path =
"/home/test1/.cache/pocl/kcache/JG/ABBLKFOBNDALGEFMHDFBNNLBFBJABFEGHNMOO/program.bc",
'\000' <repeats 374 times>...
__PRETTY_FUNCTION__ = "int
pocl_update_program_llvm_irs_unlocked(cl_program, unsigned int)"
#14 0x00007ffff3f95e3d in pocl_update_program_llvm_irs (
program=program@entry=0x750fe50, device_i=device_i@entry=0)
at ./lib/CL/pocl_llvm_wg.cc:526
lockHolder = {<No data fields>}
#15 0x00007ffff3f1b04b in compile_and_link_program (
compile_program=compile_program@entry=1,
link_program=link_program@entry=1, program=0x750fe50, num_devices=1,
device_list=0x162dd40, options=<optimized out>, num_input_headers=0,
input_headers=0x0, header_include_names=0x0, num_input_programs=0,
input_programs=0x0, pfn_notify=0x0, user_data=0x0)
at ./lib/CL/pocl_build.c:708
device = <optimized out>
found = <optimized out>
program_bc_path =
"/home/test1/.cache/pocl/kcache/JG/ABBLKFOBNDALGEFMHDFBNNLBFBJABFEGHNMOO/program.bc\000\000\000\000\000\000\350$A\354\377\177\000\000\026$A\354\377\177\000\000H$A\354\377\177",
'\000' <repeats 17 times>,
"\001p$A\354\377\177\000\000\340$A\354\377\177\000\000\310$A\354\377\177\000\000\000%A\354\377\177\000\000\001\000\000\000\000\000\000\000`\233\377\377\377\177",
'\000' <repeats 11 times>,
"\261\245\353\227\346\350\327\340$A\354\377\177\000\000"...
link_options =
"\000#A\354\377\177\000\000\000\261\245\353\227\346\350\327($A\354\377\177\000\000`\233\377\377",
'\000' <repeats 12 times>,
"@\242\377\377\377\177\000\000\000\232\377\377\377\177\000\000\377\377\377\377\377\377\377\377\000\000\000\000\000\000\000\000\070\272U\366\377\177",
'\000' <repeats 42 times>,
"\001\000\000\000\000\000\000\000@(~\366\377\177\000\000`w\272\367\377\177\000\000h\r\000\000\000\000\000\000\376uc\344\377\177\000\000\000\000\000\000\000\000\000\000\370uc\344\377\177\000\000\000\000\000\000\000\000\000\000\376uc\344\377\177\000\000\330#A\354\377\177\000\000\000\000\000\000\000\000\000\000"...
errcode = <optimized out>
error = <optimized out>
create_library = 0
requires_cr_sqrt_div = 0
spir_build = 0
flush_denorms = <optimized out>
fsize = 35924
unique_devlist = 0x162dd40
binary = 0x71fd0f0 "BC\300\336\065\024"
device_i = <optimized out>
actually_built = <optimized out>
i = <optimized out>
j = <optimized out>
build_error_code = -11
__PRETTY_FUNCTION__ = "compile_and_link_program"
#16 0x00007ffff3f1a00c in POclBuildProgram (program=<optimized out>,
num_devices=<optimized out>, device_list=<optimized out>,
options=<optimized out>, pfn_notify=<optimized out>,
user_data=<optimized out>) at ./lib/CL/clBuildProgram.c:37
No locals.
#17 0x00007fffe44cf645 in buildClProgram (source=<optimized out>,
source@entry=0x76c7fc0 "typedef union GPtr {\n __global float
*f;\n __global float2 *f2v;\n __global float4 *f4v;\n __global
float8 *f8v;\n __global float16 *f16v;\n} GPtr;\n\ntypedef union LPtr
{\n __local float *f"..., buildOpts=buildOpts@entry=0x7fffffffa670
"-g", ctx=ctx@entry=0xf9f7d0,
devID=<optimized out>, devID@entry=0xf9b050,
logBuf=logBuf@entry=0x7722cf0 "", logBufSize=logBufSize@entry=65536,
status=0x7fffffff9fe4) at ./src/library/common/clkern.c:179
program = 0x750fe50
stat = 0
#18 0x00007fffe450617f in makeKernel (device=device@entry=0xf9b050,
context=context@entry=0xf9f7d0,
kernelGenerator=kernelGenerator@entry=0x7fffe451abd0 <generator>,
program=program@entry=0x0, dims=dims@entry=0x70e9d10,
pgran=pgran@entry=0x70e9d88, extra=0x7fffffffa410,
buildOpts=0x7fffffffa670 "-g", error=0x7fffffffa270)
at ./src/library/blas/generic/common.c:476
err = 0
source = 0x76c7fc0 "typedef union GPtr {\n __global float
*f;\n __global float2 *f2v;\n __global float4 *f4v;\n __global
float8 *f8v;\n __global float16 *f16v;\n} GPtr;\n\ntypedef union LPtr
{\n __local float *f"...
size = <optimized out>
kernel = 0x7314750
log = 0x7722cf0 ""
#19 0x00007fffe4506bc0 in makeKernelCached (device=<optimized out>,
context=0xf9f7d0, sid=sid@entry=0, key=key@entry=0x7fffffffa380,
kernelGenerator=<optimized out>, dims=dims@entry=0x70e9d10,
pgran=<optimized out>, extra=<optimized out>, buildOpts=<optimized
out>,
error=<optimized out>) at ./src/library/blas/generic/common2.cc:78
kernel = <optimized out>
name = "solver0\000v\000\000\000\000\000\000\000X\216c\344"
bl = {m_cache_entry_name = "solver0", m_path = "", m_header = {
magic_key = "\004\r\"F", whole_file_size = 714668120,
header_size = 16363600, binary_size = 0,
signature_size = 16381904}, m_context = 0xf9f7d0,
m_device = 0xf9b050, m_program = 0x0, m_binary = 0x0,
m_signature = 0x0,
--Type <RET> for more, q to quit, c to continue without paging--
m_variants = std::vector of length 4, capacity 4 = {{
m_kind = BinaryLookup::INT, m_size = 4, m_data =
0x781bba0 ""}, {
m_kind = BinaryLookup::INT, m_size = 4,
m_data = 0x1c9f440 "\002"}, {m_kind = BinaryLookup::DATA,
m_size = 80, m_data = 0x6e39190 "\001"}, {
m_kind = BinaryLookup::DATA, m_size = 300,
m_data = 0x6eab760 ""}}, m_cache_enabled = false}
#20 0x00007fffe450b825 in makeSolutionSeq (funcID=funcID@entry=CLBLAS_GEMV,
args=args@entry=0x7fffffffa8d0,
numCommandQueues=numCommandQueues@entry=1,
commandQueues=commandQueues@entry=0xa70a30,
numEventsInWaitList=numEventsInWaitList@entry=0,
eventWaitList=eventWaitList@entry=0x0, events=0x7fffffffaaa8,
seq=0x7fffffffa800) at
./src/library/blas/generic/solution_seq_make.c:587
dims = 0x70e9d10
prepDims = {{x = 0, y = 0, bwidth = 10, itemX = 5, itemY = 3}, {
x = 5775357, y = 140737308720504, bwidth = 140737159574656,
itemX = 0, itemY = 0}}
ident = 0x70e9cd0
err = 0
j = <optimized out>
totalCUs = <optimized out>
numDevicesWithoutDoubles = <optimized out>
hasDouble = <optimized out>
step = 0x70e9b60
extra = {dtype = TYPE_FLOAT,
flags = (KEXTRA_COLUMN_MAJOR | KEXTRA_UPPER_TRIANG |
KEXTRA_UNIT_DIAGONAL | KEXTRA_TAILS_M | KEXTRA_BETA_ZERO |
KEXTRA_INCX_ONE | KEXTRA_INCY_ONE),
kernType = CLBLAS_COMPUTING_KERNEL, vecLen = 4, vecLenA = 4,
vecLenB = 4, vecLenC = 4, solverPriv = '\000' <repeats 15
times>,
buildOptions = "-g", '\000' <repeats 253 times>}
i = 0x70e9da8
pattern = 0x7fffe57f9ce0 <clblasSolvers>
sid = 0
key = {device = 0xf9b050, context = 0xf9f7d0, nrDims = 2,
subdims = {{
x = 1, y = 32, bwidth = 32, itemX = 1, itemY = 32}, {x = 1,
y = 4, bwidth = 4, itemX = 1, itemY = 4}, {x = 0, y = 0,
bwidth = 0, itemX = 0, itemY = 0}}}
need = {true, false, false}
ktype = CLBLAS_COMPUTING_KERNEL
kernel = <optimized out>
loadData = false
buffer = {0x0, 0x0, 0x0}
sizeBuffer = {140737328952632, 17561568, 140737328952632}
bopts = "-g", '\000' <repeats 253 times>
ik = <optimized out>
firstDimIdx = <optimized out>
#21 0x00007fffe44d79bb in doGemv (events=0x7fffffffaaa8, eventWaitList=0x0,
numEventsInWaitList=0, commandQueues=0xa70a30, numCommandQueues=1,
incy=1,
offy=0, y=0x75113e0, incx=1, offx=0, x=0x14fc830, lda=100, offA=0,
A=<optimized out>, N=128, M=100, transA=clblasNoTrans,
order=clblasColumnMajor, kargs=0x7fffffffa8d0)
at ./src/library/blas/xgemv.c:94
err = <optimized out>
seq = {prev = 0x70e9da8, next = 0x70e9da8}
sizev = 100
retCode = <optimized out>
err = <optimized out>
seq = <optimized out>
sizev = <optimized out>
retCode = <optimized out>
#22 doGemv (kargs=0x7fffffffa8d0, order=clblasColumnMajor,
transA=clblasNoTrans, M=100, N=128, A=<optimized out>, offA=0,
lda=100,
x=0x14fc830, offx=0, incx=1, y=0x75113e0, offy=0, incy=1,
numCommandQueues=1, commandQueues=0xa70a30, numEventsInWaitList=0,
eventWaitList=0x0, events=0x7fffffffaaa8) at
./src/library/blas/xgemv.c:26
err = <optimized out>
seq = <optimized out>
sizev = <optimized out>
retCode = <optimized out>
#23 0x00007fffe44d7aef in clblasSgemv (order=<optimized out>,
transA=<optimized out>, M=<optimized out>, N=128, alpha=<optimized
out>,
A=<optimized out>, offA=<optimized out>, lda=100, x=0x14fc830, offx=0,
incx=1, beta=<optimized out>, y=0x75113e0, offy=0, incy=1,
numCommandQueues=1, commandQueues=0xa70a30, numEventsInWaitList=0,
eventWaitList=0x0, events=0x7fffffffaaa8) at
./src/library/blas/xgemv.c:135
kargs = {pigFuncID = CLBLAS_GEMV, kernType =
CLBLAS_COMPUTING_KERNEL,
dtype = TYPE_FLOAT, order = clblasColumnMajor, side =
clblasLeft,
uplo = clblasUpper, transA = clblasNoTrans, transB =
clblasNoTrans,
diag = clblasUnit, M = 100, N = 128, K = 100, alpha =
{argFloat = 1,
argDouble = 5.2635442471208903e-315, argFloatComplex = {s =
{1,
0}, v2 = {1, 0}}, argDoubleComplex = {s = {
5.2635442471208903e-315, 0}, v2 =
{5.2635442471208903e-315,
0}}}, A = 0x70cafe0, lda = {matrix = 100, Vector = 100},
B = 0x14fc830, ldb = {matrix = 1, Vector = 1}, beta =
{argFloat = 0,
argDouble = 0, argFloatComplex = {s = {0, 0}, v2 = {0, 0}},
argDoubleComplex = {s = {0, 0}, v2 = {0, 0}}}, C = 0x75113e0,
ldc = {matrix = 1, Vector = 1}, D = 0x0, E = 0x0, addrBits = 0,
offsetM = 0, offsetN = 0, offsetK = 0, scimage = {0x0, 0x0},
offA = 0, offBX = 0, offCY = 0, offa = 0, offb = 0, offc = 0,
offd = 0, offe = 0, startRow = 0, endRow = 0, tailStartM = 0,
tailStartN = 0, KL = 0, KU = 0, redctnType = REDUCE_BY_SUM}
#24 0x00007ffff6886f7e in ?? () from /usr/lib/libgpuarray.so.2
No symbol table info available.
#25 0x00007ffff686d743 in GpuArray_rgemv () from /usr/lib/libgpuarray.so.2
No symbol table info available.
#26 0x00007ffff6c696d2 in ?? ()
from
/usr/lib/python3/dist-packages/pygpu/blas.cpython-37m-x86_64-linux-gnu.so
No symbol table info available.
