NVIDIA 378.13 Linux Driver Released

[L_A_G]

debianxfce (fin4478) even learns people on kernel bugzilla now how to compile kernel and advice them like here to not use stock kernels

https://bugzilla.kernel.org/show_bug.cgi?id=194579

https://bugzilla.kernel.org/show_bug.cgi?id=194559

...

Grandmaster troll So this conclusion here probably happened after his monolog there

Trolls usually don't go around using multiple monikers and admitting that they're behind these whenever someone makes the connection. He's basically just a garden variety moron/autist going around being an asshole.

[dungeon]

With new amd gpus you have no other choices.

In that bug report i don't see new hardware anywhere - it is Kaveri and Tonga, so GCN 1.1 and 1.2 or Gen 2 and 3 or gfx7/8 or year 2014... virtually minimum 1.5 year old (because of Tonga 3xx rev) or more. Both can even work with year+ dropped fglrx if they want or with amdgpu-pro, that Kaveri APU also with radeon, but also with experimental amdgpu or APU's iGPU can be disabled if someone wanna run dGPU, etc... so there are a lot of choices there. OP runs both, has fan loud bug on Tonga dGPU only - that might even interfere somehow because Kaveri is enabled also, etc...

New AMD hardware these days (since june 2016.) are Gen 4, GCN 1.3 or AI... I know you have one of these so RX 460, but not everybody has these nor you need to run Alex's kernel branches all the time nor to recommend these to everybody all the time

Also no one sane recommends Debian Testing with Ubuntu PPAs... only you do that thing.

[tuke81]

How is that OpenCL 2.0 support brewing up? I'm quite surprised there's no mention on it anywhere. In new windöws driver release notes mentions experimental support starting on driver 378.66:

OpenCL 2.0 New features in OpenCL 2.0 are available in the driver for evaluation purposes only. The following are the features as well as a description of known issues in the driver:

• Device side enqueue

•The current implementation is limited to 64-bit platforms only.
•OpenCL 2.0 allows kernels to be enqueued with global_work_size larger than the compute capability of the NVIDIA GPU. The current implementation supports only combinations of global_work_size and local_work_size that are within the compute capability of the NVIDIA GPU. The maximum supported CUDA grid and block size of NVIDIA GPUs is available at http://docs.nvidia.com/cuda/cuda-c-p...tecapabilities. For a given grid dimension, the global_work_size can be determined by CUDA grid size x CUDA block size.
•For executing kernels (whether from the host or the device), OpenCL 2.0 supports non-uniform ND-ranges where global_work_size does not need to be divisible by the local_work_size. This capability is not yet supported in the NVIDIA driver, and therefore not supported for device side kernel enqueues.

• Shared virtual memory

•The current implementation of shared virtual memory is limited to 64-bit platforms only.

While clinfo shows on my gtx750ti

$ clinfo  
Number of platforms                               1
 Platform Name                                   NVIDIA CUDA
 Platform Vendor                                 NVIDIA Corporation
 Platform Version                                OpenCL 1.2 CUDA 8.0.0
 Platform Profile                                FULL_PROFILE
 Platform Extensions                             cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int
32_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_compile
r_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts
 Platform Extensions function suffix             NV

 Platform Name                                   NVIDIA CUDA
Number of devices                                 1
 Device Name                                     GeForce GTX 750 Ti
 Device Vendor                                   NVIDIA Corporation
 Device Vendor ID                                0x10de
 Device Version                                  OpenCL 1.2 CUDA
 Driver Version                                  378.13
 Device OpenCL C Version                         OpenCL C 1.2  
 Device Type                                     GPU
 Device Profile                                  FULL_PROFILE
 Device Topology (NV)                            PCI-E, 01:00.0
 Max compute units                               5
 Max clock frequency                             1084MHz
 Compute Capability (NV)                         5.0
 Device Partition                                (core)
   Max number of sub-devices                     1
   Supported partition types                     None
 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  Yes
 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                                    64, Little-Endian
 Global memory size                              2097414144 (1.953GiB)
 Error Correction support                        No
 Max memory allocation                           524353536 (500.1MiB)
 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                        81920
 Global Memory cache line                        128 bytes
 Image support                                   Yes
   Max number of samplers per kernel             32
   Max size for 1D images from buffer            134217728 pixels
   Max 1D or 2D image array size                 2048 images
   Max 2D image size                             16384x16384 pixels
   Max 3D image size                             4096x4096x4096 pixels
   Max number of read image args                 256
   Max number of write image args                16
 Local memory type                               Local
 Local memory size                               49152 (48KiB)
 Registers per block (NV)                        65536
 Max constant buffer size                        65536 (64KiB)
 Max number of constant args                     9
 Max size of kernel argument                     4352 (4.25KiB)
 Queue properties                                
   Out-of-order execution                        Yes
   Profiling                                     Yes
 Prefer user sync for interop                    No
 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
 printf() buffer size                            1048576 (1024KiB)
 Built-in kernels                                
 Device Available                                Yes
 Compiler Available                              Yes
 Linker Available                                Yes
 Device Extensions                               cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int
32_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_compile
r_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts

NULL platform behavior
 clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  NVIDIA CUDA
 clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   Success [NV]
 clCreateContext(NULL, ...) [default]            Success [NV]
 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)  No devices found in 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                              2.2.8
 ICD loader Profile                              OpenCL 1.2
       NOTE:   your OpenCL library declares to support OpenCL 1.2,
               but it seems to support up to OpenCL 2.1 too.

[towo2099]

Again, you have really no clue! Ubuntu is not made from Debian, they rebuild all packages for ubuntu. Even the mesa-packaging in ubuntu is different fron debian, so that's why no one, bedides you, suggest ubuntu ppa's for debian. What you do on your system is your choice, but do not try to teach all other people to do it like you is doing.

[dungeon]

You are you like you wrote, a Brain dead troll and L_A_G is too.

Yeah, we are all trolls here and developers are idiots... only you are right here .

[pinguinpc]

This driver version works ok with wine 2.1 (in some titles appears improvement)