Maxwell further lowers double precision performance for GeForce GPUs

Now this double precision mockery seems to have no end. For top end Fermi based GPUs the ratio was 1/8 which was just acceptable. For the rest Fermi GPUs the ratio became 1/12. Thereafter, Kepler further reduced it to 1/24. And today we learn that the first Maxwell GPUs further cut it to 1/32!

As long as NVidia wants to sell as more Teslas as it gets we will never be able to achieve acceptable performance in double precision arithmetic from consumer cards. Actually, using a consumer GPU (excluding GTX Titan) for a compute intensive problem does not worth considering the CPU improvements with 256bit AVX2 plus the addition of FMA instructions. And certainly not everyones has 1000$ to waste for a GTX Titan. I would expect a decent double precision performance from a mid-range card of, lets say 300$, but unfortunately that's not the case.

I hope the next architecture dubbed Volta will not emply a 1/128 ratio though it doesn't actually make much difference if it is 1/32, 1/64 or 1/128. These ratios turn double precision compute on consumer cards meaningless.

Source: http://www.tomshardware.com/reviews/geforce-gtx-750-ti-review,3750.html#xtor=RSS-182

AMD Catalyst 14.1 and OpenCL SPIR

I recently noticed that the AMD Catalyst 14.1 BETA seemed to enable a very interesting extension. Look the extract of the clinfo command bellow executed on a HD-7750:

Number of platforms:     1
  Platform Profile:     FULL_PROFILE
  Platform Version:     OpenCL 1.2 AMD-APP (1411.4)
  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 cl_amd_hsa 


  Platform Name:     AMD Accelerated Parallel Processing
Number of devices:     2
  Device Type:      CL_DEVICE_TYPE_GPU
  Device ID:      4098
  Board name:      AMD Radeon HD 7700 Series   
  Device Topology:     PCI[ B#5, D#0, F#0 ]
  Max compute units:     8
  Max work items dimensions:    3
    Max work items[0]:     256
    Max work items[1]:     256
    Max work items[2]:     256
  Max work group size:     256
  Preferred vector width char:    4
  Preferred vector width short:    2
  Preferred vector width int:    1
  Preferred vector width long:    1
  Preferred vector width float:    1
  Preferred vector width double:   1
  Native vector width char:    4
  Native vector width short:    2
  Native vector width int:    1
  Native vector width long:    1
  Native vector width float:    1
  Native vector width double:    1
  Max clock frequency:     820Mhz
  Address bits:      32
  Max memory allocation:    685349273
  Image support:     Yes
  Max number of images read arguments:   128
  Max number of images write arguments:   8
  Max image 2D width:     16384
  Max image 2D height:     16384
  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:    1024
  Alignment (bits) of base address:   2048
  Minimum alignment (bytes) for any datatype:  128
  Single precision floating point capability
    Denorms:      No
    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:      16384
  Global memory size:     802160640
  Constant buffer size:     65536
  Max number of constant args:    8
  Local memory type:     Scratchpad
  Local memory size:     32768
  Kernel Preferred work group size multiple:  64
  Error correction support:    0
  Unified memory for Host and Device:   0
  Profiling timer resolution:    1
  Device endianess:     Little
  Available:      Yes
  Compiler available:     Yes
  Execution capabilities:     
    Execute OpenCL kernels:    Yes
    Execute native function:    No
  Queue properties:     
    Out-of-Order:     No
    Profiling :      Yes
  Platform ID:      0xb7446660
  Name:       Capeverde
  Vendor:      Advanced Micro Devices, Inc.
  Device OpenCL C version:    OpenCL C 1.2 
  Driver version:     1411.4 (VM)
  Profile:      FULL_PROFILE
  Version:      OpenCL 1.2 AMD-APP (1411.4)
  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_atomic_counters_32 cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_khr_spir 

Just look at look at the last line of the supported extensions of the device. There is a magic word called cl_khr_spir! Does this mean that SPIR is already supported by the driver? I don't know and I haven't performed any tests yet. Unfortunately I don't have much time to do it now but if anyone does please let me know.