Aparapi does not support OpenCL 1.2 about aparapi

[GoogleCodeExporter]

Please see 
https://groups.google.com/d/msg/aparapi-discuss/TsLsHMjGJSI/oOfiEpAzApwJ for 
additional details

Original comment by [email protected] on 3 May 2012 at 5:18

[GoogleCodeExporter]

Trunk contains source fix for this.  Will leave this as a bug (unfixed) until 
we have a binary download install.  Hopefully at the weekend I can do this.

Original comment by [email protected] on 4 May 2012 at 1:53

• Changed state: Started

[GoogleCodeExporter]

Just uploaded a new binary distribution for this.  Made from R#407 this binary 
tested on linux 32+64 and Windows 32+64.  

Original comment by [email protected] on 6 May 2012 at 6:32

• Changed state: Fixed

[GoogleCodeExporter]

Thanks Gary

Original comment by [email protected] on 6 May 2012 at 9:43

[GoogleCodeExporter]

[deleted comment]

[GoogleCodeExporter]

Adding this on behalf of [email protected] I saw it in the email list, but not 
here which is odd.  

I am still getting this error using the R#407 build. I am also using a machine 
with a Radeon HD 7970 GPU. I have no idea why that build isn't working for me 
on that machine. Here is the output from an attempted run and what I get from 
clinfo.

[mlewis@dhcp38 Test]$ scala 
-Djava.library.path=/users/mlewis/aparapi-2012-05-06 -cp 
/users/mlewis/aparapi-2012-05-06/aparapi.jar:. 
-Dcom.amd.aparapi.enableVerboseJNI=true AparapiTest
platform name    0 Advanced Micro Devices, Inc.
platform version 0 OpenCL 1.2 AMD-APP (1016.4)
platform Advanced Micro Devices, Inc. does not support requested device type 
skipping!
Nov 07, 2012 10:20:13 PM com.amd.aparapi.KernelRunner warnFallBackAndExecute
WARNING: Reverting to Java Thread Pool (JTP) for class AparapiTest$$anon$1: 
initJNI failed to return a valid handle
[mlewis@dhcp38 Test]$ clinfo
Number of platforms:                             1
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 1.2 AMD-APP (1016.4)
  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 Name:                                 AMD Accelerated Parallel Processing
Number of devices:                               1
  Device Type:                                   CL_DEVICE_TYPE_CPU
  Device ID:                                     4098
  Board name:                                   
  Max compute units:                             24
  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:                  8
  Preferred vector width double:                 4
  Native vector width char:                      16
  Native vector width short:                     8
  Native vector width int:                       4
  Native vector width long:                      2
  Native vector width float:                     8
  Native vector width double:                    4
  Max clock frequency:                           1200Mhz
  Address bits:                                  64
  Max memory allocation:                         4161392640
  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:                            16645570560
  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:                                   0x7f5d9f2dd820
  Name:                                          Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz
  Vendor:                                        GenuineIntel
  Device OpenCL C version:                       OpenCL C 1.2
  Driver version:                                1016.4 (sse2,avx)
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 1.2 AMD-APP (1016.4)
  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_3d_image_writes 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

The fact that I'm using Scala has not been a problem on other platforms. I can 
run this same program perfectly on my laptop with a much lower powered OpenCL 
1.1 card.

I appreciate any assistance. 

Original comment by [email protected] on 8 Nov 2012 at 5:45

[GoogleCodeExporter]

Can I ask a few (possibly obvious - I apologies in advance) questions, just to 
level set?

1) Have you installed the appropriate catalyst driver? It looks like you have 
installed the OpenCL SDK. Which seems to include clinfo (and apparently - but 
suprisingly seems to ship a CPU OpenCL runtime) however from the clinfo list 
above it looks like you don't have an OpenCL GPU device available. My guess is 
that you don't have an OpenCL enabled catalyst GPU driver for your card.  Or it 
would be listed in clinfo output.  

2) Have you successfully run any OpenCL (say one of the AMD provided SDK OpenCL 
samples) examples?

Certainly the error message if you *dont* have a GPU driver would look very 
similar to the issue with not having a 1.2 version of the driver. 

Gary

Original comment by [email protected] on 8 Nov 2012 at 5:57