Hi AMD,
My system specification is: Intel i3 sandybridge CPU, HD 7970 GPU, Ubuntu 12.04 OS
Device OpenCL C version: OpenCL C 1.2
Driver version: CAL 1.4.1720 (VM)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (923.1)
It may not be a serious issue, but it certainly is annoying.
Here is the backtrace when i ran it on CPU:
Program received signal SIGSEGV, Segmentation fault.
0x00007ffff613809b in llvm::ConstantArray::isString() const () from /usr/lib/libamdocl64.so
(gdb) bt
#0 0x00007ffff613809b in llvm::ConstantArray::isString() const () from /usr/lib/libamdocl64.so
#1 0x00007ffff59ad1e6 in (anonymous namespace)::AMDILPrintfConvert::expandPrintf(llvm::ilist_iterator<llvm::Instruction>*) ()
from /usr/lib/libamdocl64.so
#2 0x00007ffff59acd24 in (anonymous namespace)::AMDILPrintfConvert::runOnFunction(llvm::Function&) () from /usr/lib/libamdocl64.so
#3 0x00007ffff61dc630 in llvm::FPPassManager::runOnFunction(llvm::Function&) () from /usr/lib/libamdocl64.so
#4 0x00007ffff61dc742 in llvm::FunctionPassManagerImpl::run(llvm::Function&) () from /usr/lib/libamdocl64.so
#5 0x00007ffff61dc8d9 in llvm::FunctionPassManager::run(llvm::Function&) () from /usr/lib/libamdocl64.so
#6 0x00007ffff5482812 in amd::CompilerImpl::llvmCodeGen(llvm::Module*, std::string&, amd::CompilerTargetInfo&, llvm::JunkJITBinary**) () from /usr/lib/libamdocl64.so
#7 0x00007ffff5486e18 in amd::CompilerImpl::llvmLinkOptCG(std::string&, std::string&, amd::CompilerTargetInfo&, llvm::JunkJITBinary**) () from /usr/lib/libamdocl64.so
#8 0x00007ffff54c3f37 in gpu::NullProgram::compileBinaryToIL(amd::option::Options*) () from /usr/lib/libamdocl64.so
#9 0x00007ffff54e769c in gpu::NullProgram::linkImpl(amd::option::Options*) () from /usr/lib/libamdocl64.so
#10 0x00007ffff548ed3e in device::Program::build(std::string const&, char const*, amd::option::Options*) ()
from /usr/lib/libamdocl64.so
#11 0x00007ffff549c338 in amd::Program::build(std::vector<amd::Device*, std::allocator<amd::Device*> > const&, char const*, void (*)(_cl_program*, void*), void*, bool) () from /usr/lib/libamdocl64.so
#12 0x00007ffff547d5e7 in clBuildProgram () from /usr/lib/libamdocl64.so
Solved! Go to Solution.
The hardware has 64KB, but the largest allocation is 32KB, hence the limit.
another small bug is in clinfo output. Local Memory Size on tahiti is 64KB( it reports 32KB), GPU Max Clock is 925MHz( it reports 0MHZ).
clinfo:
Number of platforms: 2
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.2 AMD-APP (923.1)
Platform Name: AMD Accelerated Parallel Processing
Platform Vendor: Advanced Micro Devices, Inc.
Platform Extensions: cl_khr_icd cl_amd_event_callback cl_amd_offline_devices
Platform Profile: FULL_PROFILE
Platform Version: OpenCL 1.1 LINUX
Platform Name: Intel(R) OpenCL
Platform Vendor: Intel(R) Corporation
Platform Extensions: cl_khr_fp64 cl_khr_icd 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_byte_addressable_store cl_intel_printf cl_ext_device_fission cl_intel_exec_by_local_thread
Platform Name: AMD Accelerated Parallel Processing
Number of devices: 2
Device Type: CL_DEVICE_TYPE_GPU
Device ID: 4098
Board name: AMD Radeon HD 7900 Series
Device Topology: PCI[ B#1, D#0, F#0 ]
Max compute units: 32
Max work items dimensions: 3
Max work items[0]: 256
Max work items[1]: 256
Max work items[2]: 256
Max work group size: 256
Preferred vector width char: 16
Preferred vector width short: 8
Preferred vector width int: 4
Preferred vector width long: 2
Preferred vector width float: 4
Preferred vector width double: 2
Native vector width char: 16
Native vector width short: 8
Native vector width int: 4
Native vector width long: 2
Native vector width float: 4
Native vector width double: 2
Max clock frequency: 0Mhz
Address bits: 32
Max memory allocation: 536870912
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 8192
Max image 2D height: 8192
Max image 3D width: 2048
Max image 3D height: 2048
Max image 3D depth: 2048
Max samplers within kernel: 16
Max size of kernel argument: 1024
Alignment (bits) of base address: 2048
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: No
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: Yes
Cache type: Read/Write
Cache line size: 64
Cache size: 16384
Global memory size: 2147483648
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Kernel Preferred work group size multiple: 64
Error correction support: 0
Unified memory for Host and Device: 0
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: No
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0x7f658d6880a0
Name: Tahiti
Vendor: Advanced Micro Devices, Inc.
Device OpenCL C version: OpenCL C 1.2
Driver version: CAL 1.4.1720 (VM)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (923.1)
Extensions: cl_khr_fp64 cl_amd_fp64 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_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ext_atomic_counters_32 cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_popcnt
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 4098
Board name:
Max compute units: 4
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
Preferred vector width char: 16
Preferred vector width short: 8
Preferred vector width int: 4
Preferred vector width long: 2
Preferred vector width float: 4
Preferred vector width double: 0
Native vector width char: 16
Native vector width short: 8
Native vector width int: 4
Native vector width long: 2
Native vector width float: 4
Native vector width double: 0
Max clock frequency: 3300Mhz
Address bits: 64
Max memory allocation: 2147483648
Image support: Yes
Max number of images read arguments: 128
Max number of images write arguments: 8
Max image 2D width: 8192
Max image 2D height: 8192
Max image 3D width: 2048
Max image 3D height: 2048
Max image 3D depth: 2048
Max samplers within kernel: 16
Max size of kernel argument: 4096
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: Yes
Round to +ve and infinity: Yes
IEEE754-2008 fused multiply-add: Yes
Cache type: Read/Write
Cache line size: 64
Cache size: 32768
Global memory size: 4138541056
Constant buffer size: 65536
Max number of constant args: 8
Local memory type: Global
Local memory size: 32768
Kernel Preferred work group size multiple: 1
Error correction support: 0
Unified memory for Host and Device: 1
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: No
Profiling : Yes
Platform ID: 0x7f658d6880a0
Name: Intel(R) Core(TM) i3-2120 CPU @ 3.30GHz
Vendor: GenuineIntel
Device OpenCL C version: OpenCL C 1.2
Driver version: 2.0 (sse2,avx)
Profile: FULL_PROFILE
Version: OpenCL 1.2 AMD-APP (923.1)
Extensions: cl_khr_fp64 cl_amd_fp64 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_byte_addressable_store cl_khr_gl_sharing cl_ext_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_popcnt
Platform Name: Intel(R) OpenCL
Number of devices: 1
Device Type: CL_DEVICE_TYPE_CPU
Device ID: 32902
Max compute units: 4
Max work items dimensions: 3
Max work items[0]: 1024
Max work items[1]: 1024
Max work items[2]: 1024
Max work group size: 1024
Preferred vector width char: 16
Preferred vector width short: 8
Preferred vector width int: 4
Preferred vector width long: 2
Preferred vector width float: 4
Preferred vector width double: 2
Native vector width char: 16
Native vector width short: 8
Native vector width int: 4
Native vector width long: 2
Native vector width float: 4
Native vector width double: 2
Max clock frequency: 3300Mhz
Address bits: 64
Max memory allocation: 1034635264
Image support: Yes
Max number of images read arguments: 480
Max number of images write arguments: 480
Max image 2D width: 8192
Max image 2D height: 8192
Max image 3D width: 2048
Max image 3D height: 2048
Max image 3D depth: 2048
Max samplers within kernel: 480
Max size of kernel argument: 3840
Alignment (bits) of base address: 1024
Minimum alignment (bytes) for any datatype: 128
Single precision floating point capability
Denorms: Yes
Quiet NaNs: Yes
Round to nearest even: Yes
Round to zero: No
Round to +ve and infinity: No
IEEE754-2008 fused multiply-add: No
Cache type: Read/Write
Cache line size: 64
Cache size: 262144
Global memory size: 4138541056
Constant buffer size: 131072
Max number of constant args: 480
Local memory type: Global
Local memory size: 32768
Kernel Preferred work group size multiple: 128
Error correction support: 0
Unified memory for Host and Device: 1
Profiling timer resolution: 1
Device endianess: Little
Available: Yes
Compiler available: Yes
Execution capabilities:
Execute OpenCL kernels: Yes
Execute native function: Yes
Queue properties:
Out-of-Order: Yes
Profiling : Yes
Platform ID: 0x1974468
Name: Intel(R) Core(TM) i3-2120 CPU @ 3.30GHz
Vendor: Intel(R) Corporation
Device OpenCL C version: OpenCL C 1.1
Driver version: 1.1
Profile: FULL_PROFILE
Version: OpenCL 1.1 (Build 31360.31426)
Extensions: cl_khr_fp64 cl_khr_icd 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_byte_addressable_store cl_intel_printf cl_ext_device_fission cl_intel_exec_by_local_thread
IIRC one work group can access only half of LDS on Tahity.
Hi nou,
Is that so?
It would make sense to use even less LDS, so that apt number of WGs(IMHO atleast 8 wavefronts) can run on a compute Unit.
The hardware has 64KB, but the largest allocation is 32KB, hence the limit.
Please supply a test case that shows the failure so we can debug this.
Hi Micah,
I think the test case is easy to construct. I just modified bitonic sort kernel as follows and the sample crashed for me on my windows machine also.
#pragma OPENCL EXTENSION cl_amd_printf:enable
__kernel
void bitonicSort(__global uint * theArray,
const uint stage,
const uint passOfStage,
const uint width,
const uint direction)
{
uint sortIncreasing = direction;
uint threadId = get_global_id(0);
uint pairDistance = 1 << (stage - passOfStage);
uint blockWidth = 2 * pairDistance;
printf("");
uint leftId = (threadId % pairDistance)
+ (threadId / pairDistance) * blockWidth;
........
and thanks for clarifying about LOCAL Mem Size