dlprimitives
dlprimitives copied to clipboard
artyom-beilis
Support for clvk
Will this project get adapted for kpet/clvk?
$ clinfo
Number of platforms 1
Platform Name clvk
Platform Vendor clvk
Platform Version OpenCL 3.0 clvk
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_khr_extended_versioning
Platform Extensions with Version cl_khr_icd 0x400000 (1.0.0)
cl_khr_extended_versioning 0x400000 (1.0.0)
Platform Numeric Version 0xc00000 (3.0.0)
Platform Extensions function suffix clvk
Platform Host timer resolution 1ns
Platform Name clvk
Number of devices 1
Device Name llvmpipe (LLVM 20.1.3, 128 bits)
Device Vendor Mesa
Device Vendor ID 0x10005
Device Version OpenCL 3.0 CLVK on Vulkan v1.4.305 driver 1
Device UUID 6d657361-3235-2e30-2e35-000000000000
Driver UUID 6c6c766d-7069-7065-5555-494400000000
Valid Device LUID No
Device LUID 0000-000000000000
Device Node Mask 0
Device Numeric Version 0xc00000 (3.0.0)
Driver Version 3.0 CLVK on Vulkan v1.4.305 driver 1
Device OpenCL C Version OpenCL C 1.2 CLVK on Vulkan v1.4.305 driver 1
Device OpenCL C Numeric Version 0x402000 (1.2.0)
Device OpenCL C all versions OpenCL C 0x400000 (1.0.0)
OpenCL C 0x401000 (1.1.0)
OpenCL C 0x402000 (1.2.0)
OpenCL C 0xc00000 (3.0.0)
Device OpenCL C features __opencl_c_images 0xc00000 (3.0.0)
__opencl_c_3d_image_writes 0xc00000 (3.0.0)
__opencl_c_read_write_images 0xc00000 (3.0.0)
__opencl_c_atomic_order_acq_rel 0xc00000 (3.0.0)
__opencl_c_atomic_scope_device 0xc00000 (3.0.0)
__opencl_c_subgroups 0xc00000 (3.0.0)
__opencl_c_int64 0xc00000 (3.0.0)
__opencl_c_integer_dot_product_input_4x8bit 0xc00000 (3.0.0)
__opencl_c_integer_dot_product_input_4x8bit_packed 0xc00000 (3.0.0)
Latest conformance test passed v2023-12-12-00
Device Type CPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 1
Max clock frequency 0MHz
Device Partition (core)
Max number of sub-devices 0
Supported partition types None
Supported affinity domains (n/a)
Max work item dimensions 3
Max work item sizes 1024x1024x1024
Max work group size 1024
Preferred work group size multiple (device) 16
Preferred work group size multiple (kernel) 16
Max sub-groups per work group 32
Sub-group sizes (Intel) 4
Preferred / native vector sizes
char 1 / 1
short 1 / 1
int 1 / 1
long 1 / 1
half 1 / 1 (cl_khr_fp16)
float 1 / 1
double 0 / 0 (n/a)
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 Yes
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 Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Double-precision Floating-point support (n/a)
Address bits 32, Little-Endian
Global memory size 7970275328 (7.423GiB)
Error Correction support No
Max memory allocation 2147483648 (2GiB)
Unified memory for Host and Device Yes
Shared Virtual Memory (SVM) capabilities (core)
Coarse-grained buffer sharing No
Fine-grained buffer sharing No
Fine-grained system sharing No
Atomics No
Minimum alignment for any data type 128 bytes
Alignment of base address 1024 bits (128 bytes)
Preferred alignment for atomics
SVM 0 bytes
Global 0 bytes
Local 0 bytes
Atomic memory capabilities relaxed, acquire/release, work-group scope, device scope
Atomic fence capabilities relaxed, acquire/release, work-item scope, work-group scope, device scope
Max size for global variable 0
Preferred total size of global vars 0
Global Memory cache type None
Image support Yes
Max number of samplers per kernel 20
Max size for 1D images from buffer 134217728 pixels
Max 1D or 2D image array size 2048 images
Base address alignment for 2D image buffers 0 bytes
Pitch alignment for 2D image buffers 0 pixels
Max 2D image size 16384x16384 pixels
Max 3D image size 4096x4096x4096 pixels
Max number of read image args 1000000
Max number of write image args 1000000
Max number of read/write image args 1000000
Pipe support No
Max number of pipe args 0
Max active pipe reservations 0
Max pipe packet size 0
Local memory type Local
Local memory size 32768 (32KiB)
Max number of constant args 8
Max constant buffer size 65536 (64KiB)
Generic address space support No
Max size of kernel argument 1024
Queue properties (on host)
Out-of-order execution No
Profiling Yes
Device enqueue capabilities (n/a)
Queue properties (on device)
Out-of-order execution No
Profiling No
Preferred size 0
Max size 0
Max queues on device 0
Max events on device 0
Prefer user sync for interop Yes
Profiling timer resolution 1ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Non-uniform work-groups Yes
Work-group collective functions No
Sub-group independent forward progress No
IL version SPIR-V_1.0
ILs with version SPIR-V 0x400000 (1.0.0)
printf() buffer size 1048576 (1024KiB)
Built-in kernels (n/a)
Built-in kernels with version (n/a)
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_byte_addressable_store cl_khr_extended_versioning cl_khr_create_command_queue cl_khr_il_program cl_khr_spirv_no_integer_wrap_decoration cl_arm_non_uniform_work_group_size cl_arm_printf cl_khr_suggested_local_work_size cl_khr_3d_image_writes cl_khr_spirv_linkonce_odr cl_khr_device_uuid cl_khr_fp16 cl_intel_required_subgroup_size cl_khr_integer_dot_product cl_arm_integer_dot_product_int8 cl_arm_integer_dot_product_accumulate_int8 cl_arm_integer_dot_product_accumulate_saturate_int8 cl_arm_integer_dot_product_accumulate_int16
Device Extensions with Version cl_khr_global_int32_base_atomics 0x400000 (1.0.0)
cl_khr_global_int32_extended_atomics 0x400000 (1.0.0)
cl_khr_local_int32_base_atomics 0x400000 (1.0.0)
cl_khr_local_int32_extended_atomics 0x400000 (1.0.0)
cl_khr_byte_addressable_store 0x400000 (1.0.0)
cl_khr_extended_versioning 0x400000 (1.0.0)
cl_khr_create_command_queue 0x400000 (1.0.0)
cl_khr_il_program 0x400000 (1.0.0)
cl_khr_spirv_no_integer_wrap_decoration 0x400000 (1.0.0)
cl_arm_non_uniform_work_group_size 0x400000 (1.0.0)
cl_arm_printf 0x400000 (1.0.0)
cl_khr_suggested_local_work_size 0x400000 (1.0.0)
cl_khr_3d_image_writes 0x400000 (1.0.0)
cl_khr_spirv_linkonce_odr 0x400000 (1.0.0)
cl_khr_device_uuid 0x400000 (1.0.0)
cl_khr_fp16 0x400000 (1.0.0)
cl_intel_required_subgroup_size 0x400000 (1.0.0)
cl_khr_integer_dot_product 0x800000 (2.0.0)
cl_arm_integer_dot_product_int8 0x400000 (1.0.0)
cl_arm_integer_dot_product_accumulate_int8 0x400000 (1.0.0)
cl_arm_integer_dot_product_accumulate_saturate_int8 0x400000 (1.0.0)
cl_arm_integer_dot_product_accumulate_int16 0x400000 (1.0.0)
NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) clvk
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [clvk]
clCreateContext(NULL, ...) [default] Success [clvk]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name clvk
Device Name llvmpipe (LLVM 20.1.3, 128 bits)
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) Success (1)
Platform Name clvk
Device Name llvmpipe (LLVM 20.1.3, 128 bits)
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) No devices found in platform
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 clvk
Device Name llvmpipe (LLVM 20.1.3, 128 bits)
ICD loader properties
ICD loader Name OpenCL ICD Loader
ICD loader Vendor OCL Icd free software
ICD loader Version 2.3.3
ICD loader Profile OpenCL 3.0
I'm trying using pytorch_ocl to test mnist.py on ocl device with a vulkan implementation, which support cl_intel_required_subgroup_size extension, so the sgemm.cl will set the INTEL_PLATFORM to 1.
HOWEVER, the macro TILE_SIZE_K=32, and sgemm.cl will use floatK, vloadK and vstoreK, ALL UNDEFINED.
$ python mnist.py --device ocl:0
...
RuntimeError: Failed to build program source sgemm with parameters -w -cl-std=CL2.0 -DTILE_SIZE_M=32 -DTILE_SIZE_N=32 -DBLOCK_SIZE_M=4 -DBLOCK_SIZE_N=4 -DTILE_SIZE_K=32 -DTILE_OFFSET=0 -DBIAS=0 -DATRANS=0 -DBTRANS=1 -DIM2COL_OCHAN=676 -DCONVGEMM=1 -DKERN_H=3 -DKERN_W=3 -DDILATE_H=1 -DDILATE_W=1 -DPAD_H=0 -DPAD_W=0 -DSTRIDE_H=1 -DSTRIDE_W=1 -DGROUPS=1 -DCHANNELS_IN=1 -DSRC_COLS=28 -DSRC_ROWS=28 -DIMG_COLS=26 -DIMG_ROWS=26 -DREDUCE_K=1 -DACTIVATION=0 log:
For device: llvmpipe (LLVM 20.1.3, 128 bits)
source:693:31: error: expected ';' after expression
693 | floatK v=vloadK(0,&get_A(row+dr,k));
| ^
| ;
source:693:25: error: use of undeclared identifier 'floatK'
693 | floatK v=vloadK(0,&get_A(row+dr,k));
| ^
source:693:32: error: use of undeclared identifier 'v'
693 | floatK v=vloadK(0,&get_A(row+dr,k));
| ^
source:693:34: error: use of undeclared identifier 'vloadK'
693 | floatK v=vloadK(0,&get_A(row+dr,k));
| ^
source:694:25: error: use of undeclared identifier 'vstoreK'
694 | vstoreK(v,0,a[dr]);
| ^
source:694:33: error: use of undeclared identifier 'v'
694 | vstoreK(v,0,a[dr]);
|
clBuildErrorCode: -11
