dmarcuse / dynamic_ocl Goto Github PK
View Code? Open in Web Editor NEWExperimental OpenCL bindings for Rust
License: Apache License 2.0
dynamic_ocl's People
Contributors
Stargazers
Watchers
dynamic_ocl's Issues
OpenCL error -30 (CL_INVALID_VALUE), What's Wrong?
$cargo run --color=always --package dynamic_ocl --example basic
Finished dev [unoptimized + debuginfo] target(s) in 0.03s
Running `target/debug/examples/basic`
Successfully loaded OpenCL (compat level CL21)
Got platform Platform {
CL_PLATFORM_PROFILE: "FULL_PROFILE",
CL_PLATFORM_VERSION: "OpenCL 1.2 CUDA 9.1.84",
CL_PLATFORM_NAME: "NVIDIA CUDA",
CL_PLATFORM_VENDOR: "NVIDIA Corporation",
CL_PLATFORM_EXTENSIONS: "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_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer",
CL_PLATFORM_HOST_TIMER_RESOLUTION: clGetPlatformInfo: OpenCL error -30 (CL_INVALID_VALUE),
}
Got device: Device {
CL_DEVICE_TYPE: DeviceType(0b100 = GPU),
CL_DEVICE_VENDOR_ID: 4318,
CL_DEVICE_MAX_COMPUTE_UNITS: 1,
CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3,
CL_DEVICE_MAX_WORK_ITEM_SIZES: [
1024,
1024,
64,
],
CL_DEVICE_MAX_WORK_GROUP_SIZE: 1024,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR: 1,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT: 1,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT: 1,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG: 1,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT: 1,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE: 1,
CL_DEVICE_PREFERRED_VECTOR_WIDTH_HALF: 0,
CL_DEVICE_NATIVE_VECTOR_WIDTH_CHAR: 1,
CL_DEVICE_NATIVE_VECTOR_WIDTH_SHORT: 1,
CL_DEVICE_NATIVE_VECTOR_WIDTH_INT: 1,
CL_DEVICE_NATIVE_VECTOR_WIDTH_LONG: 1,
CL_DEVICE_NATIVE_VECTOR_WIDTH_FLOAT: 1,
CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE: 1,
CL_DEVICE_NATIVE_VECTOR_WIDTH_HALF: 0,
CL_DEVICE_MAX_CLOCK_FREQUENCY: 1620,
CL_DEVICE_ADDRESS_BITS: 64,
CL_DEVICE_MAX_MEM_ALLOC_SIZE: 519946240,
CL_DEVICE_IMAGE_SUPPORT: true,
CL_DEVICE_MAX_READ_IMAGE_ARGS: 128,
CL_DEVICE_MAX_WRITE_IMAGE_ARGS: 8,
CL_DEVICE_MAX_READ_WRITE_IMAGE_ARGS: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_IL_VERSION: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_IMAGE2D_MAX_WIDTH: 16384,
CL_DEVICE_IMAGE2D_MAX_HEIGHT: 16384,
CL_DEVICE_IMAGE3D_MAX_WIDTH: 2048,
CL_DEVICE_IMAGE3D_MAX_HEIGHT: 2048,
CL_DEVICE_IMAGE3D_MAX_DEPTH: 2048,
CL_DEVICE_IMAGE_MAX_BUFFER_SIZE: 134217728,
CL_DEVICE_IMAGE_MAX_ARRAY_SIZE: 2048,
CL_DEVICE_MAX_SAMPLERS: 16,
CL_DEVICE_IMAGE_PITCH_ALIGNMENT: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_IMAGE_BASE_ADDRESS_ALIGNMENT: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_MAX_PIPE_ARGS: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_PIPE_MAX_ACTIVE_RESERVATIONS: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_PIPE_MAX_PACKET_SIZE: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_MAX_PARAMETER_SIZE: 4352,
CL_DEVICE_MEM_BASE_ADDR_ALIGN: 4096,
CL_DEVICE_SINGLE_FP_CONFIG: FPConfig(0b111111 = DENORM | INF_NAN | ROUND_TO_NEAREST | ROUND_TO_ZERO | ROUND_TO_INF | FMA),
CL_DEVICE_DOUBLE_FP_CONFIG: FPConfig(0b111111 = DENORM | INF_NAN | ROUND_TO_NEAREST | ROUND_TO_ZERO | ROUND_TO_INF | FMA),
CL_DEVICE_GLOBAL_MEM_CACHE_TYPE: ReadWrite,
CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE: 128,
CL_DEVICE_GLOBAL_MEM_CACHE_SIZE: 16384,
CL_DEVICE_GLOBAL_MEM_SIZE: 2079784960,
CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 65536,
CL_DEVICE_MAX_CONSTANT_ARGS: 9,
CL_DEVICE_MAX_GLOBAL_VARIABLE_SIZE: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_GLOBAL_VARIABLE_PREFERRED_TOTAL_SIZE: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_LOCAL_MEM_TYPE: Local,
CL_DEVICE_LOCAL_MEM_SIZE: 49152,
CL_DEVICE_ERROR_CORRECTION_SUPPORT: false,
CL_DEVICE_PROFILING_TIMER_RESOLUTION: 1000,
CL_DEVICE_ENDIAN_LITTLE: true,
CL_DEVICE_AVAILABLE: true,
CL_DEVICE_LINKER_AVAILABLE: true,
CL_DEVICE_EXECUTION_CAPABILITIES: ExecutionCapabilities(0b1 = EXEC_KERNEL),
CL_DEVICE_QUEUE_ON_HOST_PROPERTIES: QueueProperties(0b11 = OUT_OF_ORDER_EXEC_MODE_ENABLE | PROFILING_ENABLE),
CL_DEVICE_QUEUE_ON_DEVICE_PROPERTIES: QueueProperties(0b11 = OUT_OF_ORDER_EXEC_MODE_ENABLE | PROFILING_ENABLE),
CL_DEVICE_QUEUE_ON_DEVICE_PREFERRED_SIZE: 262144,
CL_DEVICE_QUEUE_ON_DEVICE_MAX_SIZE: 262144,
CL_DEVICE_MAX_ON_DEVICE_QUEUES: 4,
CL_DEVICE_MAX_ON_DEVICE_EVENTS: 2048,
CL_DEVICE_BUILT_IN_KERNELS: "",
CL_DEVICE_PLATFORM: 0x000055d3ed668c20,
CL_DEVICE_NAME: "GeForce GT 730",
CL_DEVICE_VENDOR: "NVIDIA Corporation",
CL_DRIVER_VERSION: "390.132",
CL_DEVICE_PROFILE: "FULL_PROFILE",
CL_DEVICE_VERSION: "OpenCL 1.1 CUDA",
CL_DEVICE_OPENCL_C_VERSION: "OpenCL C 1.1 ",
CL_DEVICE_EXTENSIONS: "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_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer",
CL_DEVICE_PRINTF_BUFFER_SIZE: 1048576,
CL_DEVICE_PREFERRED_INTEROP_USER_SYNC: false,
CL_DEVICE_PARENT_DEVICE: 0x0000000000000000,
CL_DEVICE_PARTITION_MAX_SUB_DEVICES: 1,
CL_DEVICE_PARTITION_AFFINITY_DOMAIN: AffinityDomain(0b0 = ),
CL_DEVICE_REFERENCE_COUNT: 1,
CL_DEVICE_SVM_CAPABILITIES: SVMCapabilities(0b1 = COARSE_GRAIN_BUFFER),
CL_DEVICE_PREFERRED_PLATFORM_ATOMIC_ALIGNMENT: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_PREFERRED_GLOBAL_ATOMIC_ALIGNMENT: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_PREFERRED_LOCAL_ATOMIC_ALIGNMENT: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_MAX_NUM_SUB_GROUPS: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
CL_DEVICE_SUB_GROUP_INDEPENDENT_FORWARD_PROGRESS: clGetDeviceInfo: OpenCL error -30 (CL_INVALID_VALUE),
}
Created context: Context {
CL_CONTEXT_REFERENCE_COUNT: 1,
CL_CONTEXT_NUM_DEVICES: 1,
CL_CONTEXT_DEVICES: [
0x000055d3ed66b790,
],
}
Created command queue: Queue {
CL_QUEUE_CONTEXT: 0x000055d3ed667c30,
CL_QUEUE_DEVICE: 0x000055d3ed66b790,
CL_QUEUE_REFERENCE_COUNT: 1,
CL_QUEUE_PROPERTIES: QueueProperties(0b0 = ),
CL_QUEUE_SIZE: 0,
CL_QUEUE_DEVICE_DEFAULT: clGetCommandQueueInfo: OpenCL error -30 (CL_INVALID_VALUE),
}
Compiled program: Program(0x55d3ed946690) Ok("sum")
Build info: ProgramBuildInfo {
CL_PROGRAM_BUILD_STATUS: Success,
CL_PROGRAM_BUILD_OPTIONS: "",
CL_PROGRAM_BUILD_LOG: "\n",
CL_PROGRAM_BINARY_TYPE: Executable,
CL_PROGRAM_BUILD_GLOBAL_VARIABLE_TOTAL_SIZE: clGetProgramBuildInfo: OpenCL error -30 (CL_INVALID_VALUE),
}
Created arguments: (
Buffer<HostNoAccess, i32> {
CL_MEM_FLAGS: BufferFlagsInfo(0b1000100100 = READ_ONLY | COPY_HOST_PTR | HOST_NO_ACCESS),
CL_MEM_SIZE: 12,
CL_MEM_HOST_PTR: 0x000055d3eb84b2a8,
CL_MEM_MAP_COUNT: 0,
CL_MEM_REFERENCE_COUNT: 1,
CL_MEM_CONTEXT: 0x000055d3ed667c30,
CL_MEM_ASSOCIATED_MEMOBJECT: 0x0000000000000000,
CL_MEM_OFFSET: 0,
CL_MEM_USES_SVM_POINTER: false,
},
Buffer<HostNoAccess, i32> {
CL_MEM_FLAGS: BufferFlagsInfo(0b1000100100 = READ_ONLY | COPY_HOST_PTR | HOST_NO_ACCESS),
CL_MEM_SIZE: 12,
CL_MEM_HOST_PTR: 0x000055d3eb84b2a8,
CL_MEM_MAP_COUNT: 0,
CL_MEM_REFERENCE_COUNT: 1,
CL_MEM_CONTEXT: 0x000055d3ed667c30,
CL_MEM_ASSOCIATED_MEMOBJECT: 0x0000000000000000,
CL_MEM_OFFSET: 0,
CL_MEM_USES_SVM_POINTER: false,
},
Buffer<HostReadOnly, i32> {
CL_MEM_FLAGS: BufferFlagsInfo(0b100000010 = WRITE_ONLY | HOST_READ_ONLY),
CL_MEM_SIZE: 12,
CL_MEM_HOST_PTR: 0x0000000000000000,
CL_MEM_MAP_COUNT: 0,
CL_MEM_REFERENCE_COUNT: 1,
CL_MEM_CONTEXT: 0x000055d3ed667c30,
CL_MEM_ASSOCIATED_MEMOBJECT: 0x0000000000000000,
CL_MEM_OFFSET: 0,
CL_MEM_USES_SVM_POINTER: false,
},
)
Created and bound kernel: Kernel<(Buffer<HostNoAccess, i32>, Buffer<HostNoAccess, i32>, Buffer<HostReadOnly, i32>)> {
CL_KERNEL_FUNCTION_NAME: "sum",
CL_KERNEL_NUM_ARGS: 3,
CL_KERNEL_REFERENCE_COUNT: 1,
CL_KERNEL_CONTEXT: 0x000055d3ed667c30,
CL_KERNEL_PROGRAM: 0x000055d3ed946690,
CL_KERNEL_ATTRIBUTES: "",
}
Kernel output: [2, 4, 6]
Unloaded compiler for platform NVIDIA CUDA
Got platform Platform {
CL_PLATFORM_PROFILE: "FULL_PROFILE",
CL_PLATFORM_VERSION: "OpenCL 1.1 Mesa 20.0.8",
CL_PLATFORM_NAME: "Clover",
CL_PLATFORM_VENDOR: "Mesa",
CL_PLATFORM_EXTENSIONS: "cl_khr_icd",
CL_PLATFORM_HOST_TIMER_RESOLUTION: clGetPlatformInfo: OpenCL error -30 (CL_INVALID_VALUE),
}
thread 'main' panicked at 'called `Result::unwrap()` on an `Err` value: clGetDeviceIDs: OpenCL error -1 (CL_DEVICE_NOT_FOUND)', examples/basic.rs:25:23
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
$clinfo
Number of platforms 2
Platform Name NVIDIA CUDA
Platform Vendor NVIDIA Corporation
Platform Version OpenCL 1.2 CUDA 9.1.84
Platform Profile FULL_PROFILE
Platform Extensions 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_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer
Platform Extensions function suffix NV
Platform Name Clover
Platform Vendor Mesa
Platform Version OpenCL 1.1 Mesa 20.0.8
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd
Platform Extensions function suffix MESA
Platform Name NVIDIA CUDA
Number of devices 1
Device Name GeForce GT 730
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.1 CUDA
Driver Version 390.132
Device OpenCL C Version OpenCL C 1.1
Device Type GPU
Device Topology (NV) PCI-E, 03:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Max compute units 1
Max clock frequency 1620MHz
Compute Capability (NV) 2.1
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / native vector sizes
char 1 / 1
short 1 / 1
int 1 / 1
long 1 / 1
half 0 / 0 (n/a)
float 1 / 1
double 1 / 1 (cl_khr_fp64)
Half-precision Floating-point support (n/a)
Single-precision Floating-point support (core)
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
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 2079784960 (1.937GiB)
Error Correction support No
Max memory allocation 519946240 (495.9MiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 16384 (16KiB)
Global Memory cache line size 128 bytes
Image support Yes
Max number of samplers per kernel 16
Max 2D image size 16384x16384 pixels
Max 3D image size 2048x2048x2048 pixels
Max number of read image args 128
Max number of write image args 8
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 32768
Max number of constant args 9
Max constant buffer size 65536 (64KiB)
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) Yes
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 1
Device Extensions 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_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer
Platform Name Clover
Number of devices 0
NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) NVIDIA CUDA
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [NV]
clCreateContext(NULL, ...) [default] Success [NV]
clCreateContext(NULL, ...) [other] <error: no devices in non-default plaforms>
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) No platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) No platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) Invalid device type for platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) No platform
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
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.