We're in a catch-22.
I happened to have been using libclc-dev/libclc-amdgcn from Experimental
which are built against llvm-3.9.
Downgraded to Sid to balance the system out so now I have:
Setting up libclc-dev (0.2.0+git20150813-3) ...
Setting up libclc-amdgcn (0.2.0+git20150813-3)
Blender crashes on Mesa 13. I had forgotten those two packages were not
retrograded back down to Sid. As of now, OpenCL from Mesa is borked with
Blender 2.78a or Trunk.
clinfo is now no longer dirty with respect to the reader/producer
output: they are now synced with LLVM-3.8.1.
But until Ubuntu and Debian actually upgrade Blender to 2.78a and Mesa
14 [unless you folks are going to fold 13.1 and other unstable bits into
Sid] I'll have to wait and retest to see if the base split-kernel loads
with the OpenCL kernel crashing.
No more noise in clinfo, but no functionality either.
Sincerely,
Marc J. Driftmeyer
On 11/15/2016 07:21 AM, Andreas Boll wrote:
Control: tag -1 moreinfo
Control: reassign -1 mesa-opencl-icd 12.0.4-2
Control: retitle -1 mesa-opencl-icd: OpenCL Producer/Reader Invalid Record
On Tue, Nov 15, 2016 at 03:26:34PM +0900, Michel Dänzer wrote:
On 15/11/16 12:57 PM, Marc Jeffrey Driftmeyer wrote:
Package: libdrm-amdgpu1
Version: 2.4.71-1
Severity: normal
Dear Maintainer,
Testing Blender OpenCL with the RX 480 8GB and checking the status of it via
clinfo revealed the following error in building libdrm-amdgpu1
=== CL_PROGRAM_BUILD_LOG ===
Invalid record (Producer: 'LLVM3.9.0' Reader: 'LLVM 3.8.1') Preferred work
group size multiple Invalid record (Producer: 'LLVM3.9.0' Reader:
'LLVM 3.8.1')
Preferred / native vector sizes
This has nothing to do with libdrm-amdgpu1. It's an issue between
blender, mesa-opencl-icd, libclc-amdgcn and libllvm3.8/9.
Re-assigning to mesa-opencl-icd for now.
Which versions of blender, mesa-opencl-icd and libclc-amdgcn do you
have installed?
Please provide the complete output from clinfo. Furthermore please
follow-up using 'reportbug mesa-opencl-icd'. This way reportbug
attaches the output from mesa's bug script.
Mesa 12 and libclc from unstable currently use LLVM 3.8.1. Mesa 13
and libclc from experimental use LLVM 3.9.0. As you can see we try to
use the same LLVM version for both Mesa and libclc. So I'm not sure
what component uses LLVM 3.9.0.
Does blender use LLVM 3.9?
Do you use some packages from experimental or some self-compiled
packages?
Thanks,
Andreas
mdriftmeyer@horus:~$ clinfo
Number of platforms 2
Platform Name Clover
Platform Vendor Mesa
Platform Version OpenCL 1.1 Mesa 12.0.4
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd
Platform Extensions function suffix MESA
Platform Name Portable Computing Language
Platform Vendor The pocl project
Platform Version OpenCL 2.0 pocl 0.13, LLVM
3.8.1
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd
Platform Extensions function suffix POCL
Platform Name Clover
Number of devices 1
Device Name AMD POLARIS10 (DRM 3.3.0 /
4.8.0-1-amd64, LLVM 3.8.1)
Device Vendor AMD
Device Vendor ID 0x1002
Device Version OpenCL 1.1 Mesa 12.0.4
Driver Version 12.0.4
Device OpenCL C Version OpenCL C 1.1
Device Type GPU
Device Profile FULL_PROFILE
Max compute units 36
Max clock frequency 0MHz
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 0 / 0 (n/a)
float 4 / 4
double 2 / 2
(cl_khr_fp64)
Half-precision Floating-point support (n/a)
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
Correctly-rounded divide and sqrt operations No
Address bits 32, Little-Endian
Global memory size 1073741824 (1024MiB)
Error Correction support No
Max memory allocation 268435456 (256MiB)
Unified memory for Host and Device Yes
Minimum alignment for any data type 128 bytes
Alignment of base address 1024 bits (128 bytes)
Global Memory cache type None
Image support No
Local memory type Local
Local memory size 32768 (32KiB)
Max constant buffer size 268435456 (256MiB)
Max number of constant args 16
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 Available Yes
Compiler Available Yes
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_fp64
Platform Name Portable Computing Language
Number of devices 1
Device Name pthread-AMD FX(tm)-8350
Eight-Core Processor
Device Vendor AuthenticAMD
Device Vendor ID 0x1002
Device Version OpenCL 2.0 pocl
Driver Version 0.13
Device OpenCL C Version OpenCL C 2.0
Device Type CPU, Default
Device Profile FULL_PROFILE
Max compute units 8
Max clock frequency 4000MHz
Device Partition (core)
Max number of sub-devices 8
Supported partition types equally, by counts
Max work item dimensions 3
Max work item sizes 4096x4096x4096
Max work group size 4096
Preferred work group size multiple 8
Preferred / native vector sizes
char 16 / 16
short 8 / 8
int 4 / 4
long 2 / 2
half 8 / 8 (n/a)
float 4 / 4
double 2 / 2
(cl_khr_fp64)
Half-precision Floating-point support (n/a)
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 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
Address bits 64, Little-Endian
Global memory size 35848781824 (33.39GiB)
Error Correction support No
Max memory allocation 35848781824 (33.39GiB)
Unified memory for Host and Device Yes
Shared Virtual Memory (SVM) capabilities (core)
Coarse-grained buffer sharing Yes
Fine-grained buffer sharing Yes
Fine-grained system sharing No
Atomics Yes
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
Max size for global variable 0
Preferred total size of global vars 0
Global Memory cache type Read/Write
Global Memory cache size 16384
Global Memory cache line 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 2240548864 pixels
Max 1D or 2D image array size 2048 images
Max 2D image size 32768x32768 pixels
Max 3D image size 2048x2048x2048 pixels
Max number of read image args 128
Max number of write image args 128
Max number of read/write image args <printDeviceInfo:106: get
CL_DEVICE_MAX_READ_WRITE_IMAGE_ARGS : error -30>
Max number of pipe args 16
Max active pipe reservations 1
Max pipe packet size 1024
Local memory type Global
Local memory size 35848781824 (33.39GiB)
Max constant buffer size 35848781824 (33.39GiB)
Max number of constant args 8
Max size of kernel argument 1024
Queue properties (on host)
Out-of-order execution No
Profiling Yes
Queue properties (on device)
Out-of-order execution Yes
Profiling Yes
Preferred size 16384 (16KiB)
Max size 262144 (256KiB)
Max queues on device 1
Max events on device 1024
Prefer user sync for interop Yes
Profiling timer resolution 1ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels Yes
SPIR versions 1.2
printf() buffer size 1048576 (1024KiB)
Built-in kernels
Device Available Yes
Compiler Available Yes
Linker Available Yes
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_spir
cl_khr_int64 cl_khr_fp64 cl_khr_int64_base_atomics cl_khr_int64_extended_atomics
NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) Clover
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [MESA]
clCreateContext(NULL, ...) [default] Success [MESA]
clCreateContext(NULL, ...) [other] Success [POCL]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in
platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name Clover
Device Name AMD POLARIS10 (DRM 3.3.0 /
4.8.0-1-amd64, LLVM 3.8.1)
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 AMD POLARIS10 (DRM 3.3.0 /
4.8.0-1-amd64, LLVM 3.8.1)
ICD loader properties
ICD loader Name OpenCL ICD Loader
ICD loader Vendor OCL Icd free software
ICD loader Version 2.2.9
ICD loader Profile OpenCL 2.1
mdriftmeyer@horus:~$
