Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > comp.soft-sys.math.mathematica > #7480 > unrolled thread

CUDAImageConvolve kernel size

Started byVadim Zaliva <krokodil@gmail.com>
First post2011-12-30 12:13 +0000
Last post2011-12-30 12:13 +0000
Articles 1 — 1 participant

Back to article view | Back to comp.soft-sys.math.mathematica


Contents

  CUDAImageConvolve kernel size Vadim Zaliva <krokodil@gmail.com> - 2011-12-30 12:13 +0000

#7480 — CUDAImageConvolve kernel size

FromVadim Zaliva <krokodil@gmail.com>
Date2011-12-30 12:13 +0000
SubjectCUDAImageConvolve kernel size
Message-ID<jdk9tq$8da$1@smc.vnet.net>
I am trying to use CUDAImageConvolve as a drop-in replacement for
ImageConvolve to speed up my calculations. It appears there is a limit
on kernel size.

CUDAImageConvolve::invdim: CUDALink encountered an object with invalid
dimensions. ImageDimensions of my image are {956, 500}. If I use with
kernel 41x41 kernel, it works. However using with 101x101 kernel
produces an error:

"CUDAImageConvolve::invdim: CUDALink encountered an object with
invalid dimensions."

CUDAInformation[] reports:

{1 -> {"Name" -> "GeForce GT 330M", "Clock Rate" -> 1100000,
   "Compute Capabilities" -> 1.2, "GPU Overlap" -> 1,
   "Maximum Block Dimensions" -> {512, 512, 64},
   "Maximum Grid Dimensions" -> {65535, 65535, 1},
   "Maximum Threads Per Block" -> 512,
   "Maximum Shared Memory Per Block" -> 16384,
   "Total Constant Memory" -> 65536, "Warp Size" -> 32,
   "Maximum Pitch" -> 2147483647,
   "Maximum Registers Per Block" -> 16384, "Texture Alignment" -> 256,
    "Multiprocessor Count" -> 6, "Core Count" -> 48,
   "Execution Timeout" -> 1, "Integrated" -> False,
   "Can Map Host Memory" -> True, "Compute Mode" -> "Default",
   "Texture1D Width" -> 8192, "Texture2D Width" -> 65536,
   "Texture2D Height" -> 32768, "Texture3D Width" -> 2048,
   "Texture3D Height" -> 2048, "Texture3D Depth" -> 2048,
   "Texture2D Array Width" -> 8192, "Texture2D Array Height" -> 8192,
   "Texture2D Array Slices" -> 512, "Surface Alignment" -> 256,
   "Concurrent Kernels" -> False, "ECC Enabled" -> False,
   "TCC Enabled" -> False, "Total Memory" -> 536543232}}

"Maximum Block Dimensions" may be interpreted as kernel size limit,
but I am well below that. Any suggestions?

Thanks!

[toc] | [standalone]


Back to top | Article view | comp.soft-sys.math.mathematica


csiph-web