$ DEVICE="opencl0:0" python -c "import pygpu;pygpu.test()" pygpu is installed in /usr/lib64/python2.7/site-packages/pygpu-0.6.2-py2.7-linux-x86_64.egg/pygpu NumPy version 1.11.2 NumPy relaxed strides checking option: False NumPy is installed in /usr/lib64/python2.7/site-packages/numpy Python version 2.7.13 (default, Jan 12 2017, 17:59:37) [GCC 6.3.1 20161221 (Red Hat 6.3.1-1)] nose version 1.3.7 *** Testing for AMD FIJI (DRM 3.8.0 / 4.9.13-200.fc25.x86_64, LLVM 5.0.0) ======================================================== AN INTERNAL KERNEL BUILD ERROR OCCURRED! device name = AMD FIJI (DRM 3.8.0 / 4.9.13-200.fc25.x86_64, LLVM 5.0.0) error = -43 memory pattern = Register accumulation based swap, computing kernel generator Subproblem dimensions: dims[0].itemY = 32, dims[0].itemX = 32, dims[0].y = 32, dims[0].x = 32, dims[0].bwidth = 64; ; dims[1].itemY = 4, dims[1].itemX = 4, dims[1].y = 4, dims[1].x = 4, dims[1].bwidth = 8; ; Parallelism granularity: pgran->wgDim = 1, pgran->wgSize[0] = 64, pgran->wgSize[1] = 1, pgran->wfSize = 64 Kernel extra flags: 369130144 Source: #ifdef DOUBLE_PRECISION #ifdef cl_khr_fp64 #pragma OPENCL EXTENSION cl_khr_fp64 : enable #else #pragma OPENCL EXTENSION cl_amd_fp64 : enable #endif #endif __kernel void Sdot_kernel( __global float *_X, __global float *_Y, __global float *scratchBuff, uint N, uint offx, int incx, uint offy, int incy, int doConj ) { __global float *X = _X + offx; __global float *Y = _Y + offy; float dotP = (float) 0.0; if ( incx < 0 ) { X = X + (N - 1) * abs(incx); } if ( incy < 0 ) { Y = Y + (N - 1) * abs(incy); } int gOffset; for( gOffset=(get_global_id(0) * 4); (gOffset + 4 - 1)<N; gOffset+=( get_global_size(0) * 4 ) ) { float4 vReg1, vReg2, res; #ifdef INCX_NONUNITY vReg1 = (float4)( (X + (gOffset*incx))[0 + ( incx * 0)], (X + (gOffset*incx))[0 + ( incx * 1)], (X + (gOffset*incx))[0 + ( incx * 2)], (X + (gOffset*incx))[0 + ( incx * 3)]); #else vReg1 = vload4( 0, (__global float *) (X + gOffset) ); #endif #ifdef INCY_NONUNITY vReg2 = (float4)( (Y + (gOffset*incy))[0 + ( incy * 0)], (Y + (gOffset*incy))[0 + ( incy * 1)], (Y + (gOffset*incy))[0 + ( incy * 2)], (Y + (gOffset*incy))[0 + ( incy * 3)]); #else vReg2 = vload4( 0, (__global float *) (Y + gOffset) ); #endif ; res = vReg1 * vReg2 ; dotP += res .S0 + res .S1 + res .S2 + res .S3; ; // Add-up elements in the vector to give a scalar } // Loop for the last thread to handle the tail part of the vector // Using the same gOffset used above for( ; gOffset<N; gOffset++ ) { float sReg1, sReg2, res; sReg1 = X[gOffset * incx]; sReg2 = Y[gOffset * incy]; ; res = sReg1 * sReg2 ; dotP = dotP + res ; } // Note: this has to be called outside any if-conditions- because REDUCTION uses barrier // dotP of work-item 0 will have the final reduced item of the work-group __local float viraW [ 64 ]; uint kFbwL = get_local_id(0); viraW [ kFbwL ] = dotP ; barrier(CLK_LOCAL_MEM_FENCE); if( kFbwL < 32 ) { viraW [ kFbwL ] = viraW [ kFbwL ] + viraW [ kFbwL + 32 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( kFbwL < 16 ) { viraW [ kFbwL ] = viraW [ kFbwL ] + viraW [ kFbwL + 16 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( kFbwL < 8 ) { viraW [ kFbwL ] = viraW [ kFbwL ] + viraW [ kFbwL + 8 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( kFbwL < 4 ) { viraW [ kFbwL ] = viraW [ kFbwL ] + viraW [ kFbwL + 4 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( kFbwL < 2 ) { viraW [ kFbwL ] = viraW [ kFbwL ] + viraW [ kFbwL + 2 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( kFbwL == 0 ) { dotP = viraW [0] + viraW [1]; } if( (get_local_id(0)) == 0 ) { scratchBuff[ get_group_id(0) ] = dotP; } } -------------------------------------------------------- Build log: ======================================================== Segmentation fault (core dumped)
*** Testing for AMD Radeon R7 Graphics (CARRIZO / DRM 3.18.0 / 4.11.0-ROC, LLVM 5.0.0) Ran 6670 tests in 785.274s FAILED (SKIP=12, errors=580, failures=12) all errors are caused by: TypeError: This is for CUDA arrays. I haven't investigated the failures. There are couple of patches needed: https://github.com/Theano/libgpuarray/pull/534 https://github.com/Theano/libgpuarray/pull/535 http://lists.llvm.org/pipermail/libclc-dev/2017-September/002449.html and: diff --git a/src/cluda_opencl.h b/src/cluda_opencl.h index 6e0095c..e93aa8b 100644 --- a/src/cluda_opencl.h +++ b/src/cluda_opencl.h @@ -48,9 +48,9 @@ typedef struct _ga_half { } ga_half; #define ga_half2float(p) vload_half(0, &((p).data)) -static inline ga_half ga_float2half(ga_float f) { +inline ga_half ga_float2half(ga_float f) { ga_half r; - vstore_half_rtn(f, 0, &r.data); + vstore_half(f, 0, &r.data); return r; } diff --git a/src/gpuarray_buffer_opencl.c b/src/gpuarray_buffer_opencl.c index 8f12811..2041ca2 100644 --- a/src/gpuarray_buffer_opencl.c +++ b/src/gpuarray_buffer_opencl.c @@ -146,7 +146,7 @@ cl_ctx *cl_make_ctx(cl_context ctx, gpucontext_props *p) { CL_CHECKN(global_err, clGetDeviceInfo(id, CL_DEVICE_VERSION, device_version_size, device_version, NULL)); - if (device_version[7] == '1' && device_version[9] < '2') { + if (device_version[7] == '1' && device_version[9] < '1') { error_set(global_err, GA_UNSUPPORTED_ERROR, "We only support OpenCL 1.2 and up"); return NULL;
Latest update: diff --git a/src/cluda_opencl.h b/src/cluda_opencl.h index 6e0095c..8ba2d14 100644 --- a/src/cluda_opencl.h +++ b/src/cluda_opencl.h @@ -48,7 +48,7 @@ typedef struct _ga_half { } ga_half; #define ga_half2float(p) vload_half(0, &((p).data)) -static inline ga_half ga_float2half(ga_float f) { +inline ga_half ga_float2half(ga_float f) { ga_half r; vstore_half_rtn(f, 0, &r.data); return r; diff --git a/src/gpuarray_buffer_opencl.c b/src/gpuarray_buffer_opencl.c index 8f12811..2041ca2 100644 --- a/src/gpuarray_buffer_opencl.c +++ b/src/gpuarray_buffer_opencl.c @@ -146,7 +146,7 @@ cl_ctx *cl_make_ctx(cl_context ctx, gpucontext_props *p) { CL_CHECKN(global_err, clGetDeviceInfo(id, CL_DEVICE_VERSION, device_version_size, device_version, NULL)); - if (device_version[7] == '1' && device_version[9] < '2') { + if (device_version[7] == '1' && device_version[9] < '1') { error_set(global_err, GA_UNSUPPORTED_ERROR, "We only support OpenCL 1.2 and up"); return NULL >>> pygpu.test() pygpu is installed in /home/jvesely/.local/lib/python3.6/site-packages/pygpu-0.7.5+12.g6f0132c.dirty-py3.6-linux-x86_64.egg/pygpu NumPy version 1.13.3 NumPy relaxed strides checking option: True NumPy is installed in /usr/lib64/python3.6/site-packages/numpy Python version 3.6.4 (default, Mar 13 2018, 18:18:20) [GCC 7.3.1 20180303 (Red Hat 7.3.1-5)] nose version 1.3.7 *** Testing for AMD Radeon R7 Graphics (CARRIZO / DRM 3.23.0 / 4.15.14-300.fc27.x86_64, LLVM 6.0.0) ---------------------------------------------------------------------- Ran 6670 tests in 995.728s FAILED (SKIP=12, errors=580, failures=2) All errors are: TypeError: This is for CUDA arrays. The two failures are: FAIL: pygpu.tests.test_elemwise.test_elemwise_f16(<built-in function add>, 'float16', 'float16', (50,)) FAIL: pygpu.tests.test_elemwise.test_elemwise_f16(<built-in function iadd>, 'float16', 'float16', (50,)) Which fail on half precision rounding error. for example: 7.0390625+7.20703125 is expected to be 14.25 but gpu returns 14.2421875 the fp32 result is 14.24609375. The GPU result is rounded down (towards zero) The CPU result is rounded up (away from zero) It looks like our vstore_half_rtn is not working as expected, which is weird because it passes CTS.
(In reply to Jan Vesely from comment #2) > It looks like our vstore_half_rtn is not working as expected, which is weird > because it passes CTS. I take this back. vstore_half_rtn rounds to negative infinity (towards 0 for positive numbers). Changing line 53 in cluda_opencl.h: - vstore_half_rtn(f, 0, &r.data); + vstore_half_rte(f, 0, &r.data); fixes the two failures. Other than advertising OCL1.2 the remaining failures are NOTOURBUG.
Lowering CL requirements combined with the following pull requests: https://github.com/Theano/libgpuarray/pull/571 https://github.com/Theano/libgpuarray/pull/570 Results in: Ran 4970 tests in 1158.909s OK (SKIP=12)
(In reply to Jan Vesely from comment #4) > Lowering CL requirements combined with the following pull requests: > https://github.com/Theano/libgpuarray/pull/571 > https://github.com/Theano/libgpuarray/pull/570 Both above pull requests have been merged with slight modifications. running CLOVER_DEVICE_VERSION_OVERRIDE=1.2 CLOVER_DEVICE_CLC_VERSION_OVERRIDE=1.2 results in: Ran 6670 tests in 991.622s OK (SKIP=12)
Seems the error is still there: CLOVER_DEVICE_VERSION_OVERRIDE=1.2 CLOVER_DEVICE_CLC_VERSION_OVERRIDE=1.2 DEVICE="opencl0:0" python3 -c "import pygpu;pygpu.test()" fails with: pygpu is installed in /usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu NumPy version 1.16.3 NumPy relaxed strides checking option: True NumPy is installed in /home/nano/.local/lib/python3.6/site-packages/numpy Python version 3.6.7 (default, Oct 22 2018, 11:32:17) [GCC 8.2.0] nose version 1.3.7 *** Testing for Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 5.1.0-rc5+, LLVM 8.0.0) mpi4py found: True ................................................. ======================================================== AN INTERNAL KERNEL BUILD ERROR OCCURRED! device name = Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 5.1.0-rc5+, LLVM 8.0.0) error = -43 memory pattern = Register accumulation based swap, computing kernel generator Subproblem dimensions: dims[0].itemY = 32, dims[0].itemX = 32, dims[0].y = 32, dims[0].x = 32, dims[0].bwidth = 64; ; dims[1].itemY = 4, dims[1].itemX = 4, dims[1].y = 4, dims[1].x = 4, dims[1].bwidth = 8; ; Parallelism granularity: pgran->wgDim = 1, pgran->wgSize[0] = 64, pgran->wgSize[1] = 1, pgran->wfSize = 64 Kernel extra flags: 369130144 Source: #ifdef DOUBLE_PRECISION #ifdef cl_khr_fp64 #pragma OPENCL EXTENSION cl_khr_fp64 : enable #else #pragma OPENCL EXTENSION cl_amd_fp64 : enable #endif #endif __kernel void Sdot_kernel( __global float *_X, __global float *_Y, __global float *scratchBuff, uint N, uint offx, int incx, uint offy, int incy, int doConj ) { __global float *X = _X + offx; __global float *Y = _Y + offy; float dotP = (float) 0.0; if ( incx < 0 ) { X = X + (N - 1) * abs(incx); } if ( incy < 0 ) { Y = Y + (N - 1) * abs(incy); } int gOffset; for( gOffset=(get_global_id(0) * 4); (gOffset + 4 - 1)<N; gOffset+=( get_global_size(0) * 4 ) ) { float4 vReg1, vReg2, res; #ifdef INCX_NONUNITY vReg1 = (float4)( (X + (gOffset*incx))[0 + ( incx * 0)], (X + (gOffset*incx))[0 + ( incx * 1)], (X + (gOffset*incx))[0 + ( incx * 2)], (X + (gOffset*incx))[0 + ( incx * 3)]); #else vReg1 = vload4( 0, (__global float *) (X + gOffset) ); #endif #ifdef INCY_NONUNITY vReg2 = (float4)( (Y + (gOffset*incy))[0 + ( incy * 0)], (Y + (gOffset*incy))[0 + ( incy * 1)], (Y + (gOffset*incy))[0 + ( incy * 2)], (Y + (gOffset*incy))[0 + ( incy * 3)]); #else vReg2 = vload4( 0, (__global float *) (Y + gOffset) ); #endif ; res = vReg1 * vReg2 ; dotP += res .S0 + res .S1 + res .S2 + res .S3; ; // Add-up elements in the vector to give a scalar } // Loop for the last thread to handle the tail part of the vector // Using the same gOffset used above for( ; gOffset<N; gOffset++ ) { float sReg1, sReg2, res; sReg1 = X[gOffset * incx]; sReg2 = Y[gOffset * incy]; ; res = sReg1 * sReg2 ; dotP = dotP + res ; } // Note: this has to be called outside any if-conditions- because REDUCTION uses barrier // dotP of work-item 0 will have the final reduced item of the work-group __local float bixzI [ 64 ]; uint yBrfY = get_local_id(0); bixzI [ yBrfY ] = dotP ; barrier(CLK_LOCAL_MEM_FENCE); if( yBrfY < 32 ) { bixzI [ yBrfY ] = bixzI [ yBrfY ] + bixzI [ yBrfY + 32 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( yBrfY < 16 ) { bixzI [ yBrfY ] = bixzI [ yBrfY ] + bixzI [ yBrfY + 16 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( yBrfY < 8 ) { bixzI [ yBrfY ] = bixzI [ yBrfY ] + bixzI [ yBrfY + 8 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( yBrfY < 4 ) { bixzI [ yBrfY ] = bixzI [ yBrfY ] + bixzI [ yBrfY + 4 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( yBrfY < 2 ) { bixzI [ yBrfY ] = bixzI [ yBrfY ] + bixzI [ yBrfY + 2 ]; } barrier(CLK_LOCAL_MEM_FENCE); if( yBrfY == 0 ) { dotP = bixzI [0] + bixzI [1]; } if( (get_local_id(0)) == 0 ) { scratchBuff[ get_group_id(0) ] = dotP; } } -------------------------------------------------------- Build log: ======================================================== [nano2:28210] *** Process received signal *** [nano2:28210] Signal: Segmentation fault (11) [nano2:28210] Signal code: Address not mapped (1) [nano2:28210] Failing at address: (nil) [nano2:28210] [ 0] /lib/x86_64-linux-gnu/libc.so.6(+0x3ef20)[0x7fbff3a90f20] [nano2:28210] [ 1] /usr/lib/x86_64-linux-gnu/libclBLAS.so(makeKernelCached+0x2a0)[0x7fbf9eaefcf0] [nano2:28210] [ 2] /usr/lib/x86_64-linux-gnu/libclBLAS.so(makeSolutionSeq+0x101b)[0x7fbf9eaf445b] [nano2:28210] [ 3] /usr/lib/x86_64-linux-gnu/libclBLAS.so(doDot+0x2b2)[0x7fbf9ead7c52] [nano2:28210] [ 4] /usr/lib/x86_64-linux-gnu/libclBLAS.so(clblasSdot+0x98)[0x7fbf9ead7da8] [nano2:28210] [ 5] /home/nano/.local/lib/libgpuarray.so.3(+0x32529)[0x7fbff23aa529] [nano2:28210] [ 6] /home/nano/.local/lib/libgpuarray.so.3(GpuArray_rdot+0x393)[0x7fbff23879f3] [nano2:28210] [ 7] /usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu/blas.cpython-36m-x86_64-linux-gnu.so(+0x6032)[0x7fbf9c0fa032] [nano2:28210] [ 8] /usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu/blas.cpython-36m-x86_64-linux-gnu.so(+0x67ba)[0x7fbf9c0fa7ba] [nano2:28210] [ 9] python3[0x5030d5] [nano2:28210] [10] python3(_PyEval_EvalFrameDefault+0x1231)[0x507641] [nano2:28210] [11] python3[0x504c28] [nano2:28210] [12] python3[0x58650d] [nano2:28210] [13] python3(PyObject_Call+0x3e)[0x59ebbe] [nano2:28210] [14] python3(_PyEval_EvalFrameDefault+0x1807)[0x507c17] [nano2:28210] [15] python3[0x504c28] [nano2:28210] [16] python3[0x58644b] [nano2:28210] [17] python3(PyObject_Call+0x3e)[0x59ebbe] [nano2:28210] [18] python3(_PyEval_EvalFrameDefault+0x1807)[0x507c17] [nano2:28210] [19] python3[0x502209] [nano2:28210] [20] python3[0x502f3d] [nano2:28210] [21] python3(_PyEval_EvalFrameDefault+0x449)[0x506859] [nano2:28210] [22] python3[0x504c28] [nano2:28210] [23] python3(_PyFunction_FastCallDict+0x2de)[0x501b2e] [nano2:28210] [24] python3[0x591461] [nano2:28210] [25] python3(PyObject_Call+0x3e)[0x59ebbe] [nano2:28210] [26] python3(_PyEval_EvalFrameDefault+0x1807)[0x507c17] [nano2:28210] [27] python3[0x504c28] [nano2:28210] [28] python3(_PyFunction_FastCallDict+0x2de)[0x501b2e] [nano2:28210] [29] python3[0x591461] [nano2:28210] *** End of error message *** Speicherzugriffsfehler (Speicherabzug geschrieben)
Running https://github.com/ZVK/sampleRNN_ICLR2017 fails with: Traceback (most recent call last): File "models/two_tier/two_tier32k.py", line 429, in <module> on_unused_input='warn' File "/home/nano/rust/mesa/Theano/theano/compile/function.py", line 317, in function output_keys=output_keys) File "/home/nano/rust/mesa/Theano/theano/compile/pfunc.py", line 486, in pfunc output_keys=output_keys) File "/home/nano/rust/mesa/Theano/theano/compile/function_module.py", line 1841, in orig_function fn = m.create(defaults) File "/home/nano/rust/mesa/Theano/theano/compile/function_module.py", line 1715, in create input_storage=input_storage_lists, storage_map=storage_map) File "/home/nano/rust/mesa/Theano/theano/gof/link.py", line 699, in make_thunk storage_map=storage_map)[:3] File "/home/nano/rust/mesa/Theano/theano/gof/vm.py", line 1091, in make_all impl=impl)) File "/home/nano/rust/mesa/Theano/theano/gof/op.py", line 955, in make_thunk no_recycling) File "/home/nano/rust/mesa/Theano/theano/gof/op.py", line 858, in make_c_thunk output_storage=node_output_storage) File "/home/nano/rust/mesa/Theano/theano/gof/cc.py", line 1217, in make_thunk keep_lock=keep_lock) File "/home/nano/rust/mesa/Theano/theano/gof/cc.py", line 1157, in __compile__ keep_lock=keep_lock) File "/home/nano/rust/mesa/Theano/theano/gof/cc.py", line 1641, in cthunk_factory *(in_storage + out_storage + orphd)) RuntimeError: ('The following error happened while compiling the node', GpuCrossentropySoftmaxArgmax1HotWithBias(GpuDot22.0, SampleLevel.Output.b, GpuReshape{1}.0), '\n', 'GpuKernel_init error 3: clBuildProgram: Unknown error')
I'm using mesa and linux master git on ubuntu 18.04.2 Theano and libgpuarray are installed from git as well. The changes you have made in the past are still there. Any idea what could be wrong now?
Just in case it is of any importance: clinfo Number of platforms 1 Platform Name Clover Platform Vendor Mesa Platform Version OpenCL 1.1 Mesa 19.1.0-devel (git-a6ccc4c 2019-04-21 bionic-oibaf-ppa) Platform Profile FULL_PROFILE Platform Extensions cl_khr_icd Platform Extensions function suffix MESA Platform Name Clover Number of devices 1 Device Name Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 5.1.0-rc5+, LLVM 8.0.0) Device Vendor AMD Device Vendor ID 0x1002 Device Version OpenCL 1.1 Mesa 19.1.0-devel (git-a6ccc4c 2019-04-21 bionic-oibaf-ppa) Driver Version 19.1.0-devel Device OpenCL C Version OpenCL C 1.1 Device Type GPU Device Profile FULL_PROFILE Device Available Yes Compiler Available Yes Max compute units 16 Max clock frequency 1300MHz Max work item dimensions 3 Max work item sizes 256x256x256 Max work group size 256 Preferred work group size multiple 64 Preferred / native vector sizes char 16 / 16 short 8 / 8 int 4 / 4 long 2 / 2 half 8 / 8 (cl_khr_fp16) float 4 / 4 double 2 / 2 (cl_khr_fp64) Half-precision Floating-point support (cl_khr_fp16) Denormals No Infinity and NANs Yes Round to nearest Yes Round to zero No Round to infinity No IEEE754-2008 fused multiply-add No Support is emulated in software No Single-precision Floating-point support (core) Denormals No Infinity and NANs Yes Round to nearest Yes Round to zero No Round to infinity No IEEE754-2008 fused multiply-add No Support is emulated in software No Correctly-rounded divide and sqrt operations No Double-precision Floating-point support (cl_khr_fp64) Denormals Yes Infinity and NANs Yes Round to nearest Yes Round to zero Yes Round to infinity Yes IEEE754-2008 fused multiply-add Yes Support is emulated in software No Address bits 64, Little-Endian Global memory size 4294967296 (4GiB) Error Correction support No Max memory allocation 3435973836 (3.2GiB) Unified memory for Host and Device No Minimum alignment for any data type 128 bytes Alignment of base address 32768 bits (4096 bytes) Global Memory cache type None Image support No Local memory type Local Local memory size 32768 (32KiB) Max number of constant args 16 Max constant buffer size 2147483647 (2GiB) Max size of kernel argument 1024 Queue properties Out-of-order execution No Profiling Yes Profiling timer resolution 0ns Execution capabilities Run OpenCL kernels Yes Run native kernels No Device Extensions cl_khr_byte_addressable_store cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64 cl_khr_fp16 NULL platform behavior clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) Clover clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [MESA] clCreateContext(NULL, ...) [default] Success [MESA] clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1) Platform Name Clover Device Name Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 5.1.0-rc5+, LLVM 8.0.0) clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1) Platform Name Clover Device Name Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 5.1.0-rc5+, LLVM 8.0.0) clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1) Platform Name Clover Device Name Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 5.1.0-rc5+, LLVM 8.0.0) ICD loader properties ICD loader Name OpenCL ICD Loader ICD loader Vendor OCL Icd free software ICD loader Version 2.2.11 ICD loader Profile OpenCL 2.1
Just to make extra sure its most likely a problem with clover I installed the AMD legacy opencl driver in parallel (works fine): DEVICE="opencl1:0" python3 -c "import pygpu;pygpu.test()" pygpu is installed in /usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu NumPy version 1.16.3 NumPy relaxed strides checking option: True NumPy is installed in /home/nano/.local/lib/python3.6/site-packages/numpy Python version 3.6.7 (default, Oct 22 2018, 11:32:17) [GCC 8.2.0] nose version 1.3.7 *** Testing for Baffin mpi4py found: True .........................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................SSSSSSSSSSS................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................ ---------------------------------------------------------------------- Ran 7300 tests in 101.882s OK (SKIP=11)
It has been some time that I ran theano. Does the error happen even if it's built without clBLAS support? clBLAS depends on CL1.2 features which are not implemented, yet. (hence the dependence on 94273)
Seems about right CLOVER_DEVICE_VERSION_OVERRIDE=1.2 CLOVER_DEVICE_CLC_VERSION_OVERRIDE=1.2 DEVICE="opencl0:0" python3 -c "import pygpu;pygpu.test()" pygpu is installed in /usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu NumPy version 1.16.3 NumPy relaxed strides checking option: True NumPy is installed in /home/nano/.local/lib/python3.6/site-packages/numpy Python version 3.6.7 (default, Oct 22 2018, 11:32:17) [GCC 8.2.0] nose version 1.3.7 *** Testing for Radeon RX 560 Series (POLARIS11, DRM 3.30.0, 4.15.0-47-generic, LLVM 8.0.0) mpi4py found: True .................................................EEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEESSSSSSSSSSS................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................................ ====================================================================== ERROR: pygpu.tests.test_blas.test_dot(1, 'float32', True, True, True, False) ---------------------------------------------------------------------- Traceback (most recent call last): File "/usr/lib/python3/dist-packages/nose/case.py", line 197, in runTest self.test(*self.arg) File "/usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu/tests/test_blas.py", line 22, in f func(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/pygpu-0.7.6+20.g9cec614-py3.6-linux-x86_64.egg/pygpu/tests/test_blas.py", line 56, in dot gr = gblas.dot(gX, gY, gZ, overwrite_z=overwrite) File "pygpu/blas.pyx", line 79, in pygpu.blas.dot File "pygpu/blas.pyx", line 29, in pygpu.blas.pygpu_blas_rdot pygpu.gpuarray.GpuArrayException: (b'Missing Blas library', 5) ... Ran 7300 tests in 972.999s FAILED (SKIP=11, errors=584)
Unfortunately it turns out that even a working opencl (used the closed AMD legacy driver) isnt getting the application i'm trying to run (see above) to work. At some point it complains that a data structure requires cuda (somewhere in libgpuarray). Which could probably be fixed if theano was still being maintained. Which it sort of isnt (pymc3 still uses it and they want to maintain what they use of it) However pymc4 is using tensorflow which as AFAICT is CUDA only. So what I really want is probably cuda on opencl (https://github.com/hughperkins/coriander) but that requires opencl 1.2. back to square one ;)
-- GitLab Migration Automatic Message -- This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity. You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/mesa/mesa/issues/137.
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.