Dear Alexander, Currently i'm running on server with Tesla M2075, the device config is the following CUDA Driver Version / Runtime Version 7.0 / 7.0 CUDA Capability Major/Minor version number: 2.0 Total amount of global memory: 5375 MBytes (5636554752 bytes) (14) Multiprocessors, ( 32) CUDA Cores/MP: 448 CUDA Cores GPU Max Clock rate: 1147 MHz (1.15 GHz) Memory Clock rate: 1566 Mhz Memory Bus Width: 384-bit L2 Cache Size: 786432 bytes Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65535), 3D=(2048, 2048, 2048) Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers Total amount of constant memory: 65536 bytes Total amount of shared memory per block: 49152 bytes Total number of registers available per block: 32768 Warp size: 32 Maximum number of threads per multiprocessor: 1536 Maximum number of threads per block: 1024 Max dimension size of a thread block (x,y,z): (1024, 1024, 64) Max dimension size of a grid size (x,y,z): (65535, 65535, 65535) Maximum memory pitch: 2147483647 bytes Texture alignment: 512 bytes Concurrent copy and kernel execution: Yes with 2 copy engine(s) Run time limit on kernels: No Integrated GPU sharing Host Memory: No Support host page-locked memory mapping: Yes Alignment requirement for Surfaces: Yes Device has ECC support: Enabled Device supports Unified Addressing (UVA): Yes Device PCI Domain ID / Bus ID / location ID: 0 / 8 / 0 Thanks On Thu, Dec 17, 2015 at 5:26 PM, Alexander Monakov <amonakov@xxxxxxxxx> wrote: > On Thu, 17 Dec 2015, Esteban Hernández wrote: > >> Dear, >> >> I compile gcc 6 r231616, for offloading and host, >> >> >> When i compile a simple example with -fopenacc -foffload=nvptx-none >> >> The compilation process finish o.k, but when i Run the code in a >> machine with cuda device, obtain the following problem >> >> >> libgomp: cuModuleLoadData error: device kernel image is invalid > > Are you perhaps using new Maxwell-generation GPU for testing (Geforce 750, > 950+)? There's odd code in libgomp plugin that insists on producing binary > code for Kepler-class hardware only. > > Nathan, is that a mistake, or was there some reason to fix JIT target? We are > removing that code on gomp-nvptx branch: > https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=1099ad42d145faf428053018d02b26678c47adce > > Alexander -- Sincerely Esteban Hernandez B. HPC specialist
