Forum > Windows
optimized sources
Jason G:
Cheers Heinz. This should really be released already (for a while), but I have some hectic schedule preventing my full attention to do things right. I hope to sort things out soon so we can move onto the next stage.
Jason
_heinz:
how p8 compiles:
p8 - New Optimizations for 32-bit applications on 45nm Intel® Core™2 Duo (Penryn,Nehalem,Westmere) family processors
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1>------ Neues Erstellen gestartet: Projekt: ap_client, Konfiguration: AP_SSE2_CSP_QaxAVX Win32 ------
1>Deleting intermediate files and output files for project 'ap_client', configuration 'AP_SSE2_CSP_QaxAVX|Win32'.
1>AP SSE2_IPP_ICC_CSP_QaxSSE2_Qparallel_MKLP_BLANKIT_O2_Oii Win32 (Microsoft VC++ Environment)
1>Generating new BuildInfo
1>SubWCRev: 'C:\I\SC\apwk\ap_ICCIPP'
1>Last committed at revision 374
1>Updated to revision 374
1>Local modifications found
1>
1>APREV IS 374
1>Deleting old output files
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_schema.cpp
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_fold.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>intrinsics.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_fileio.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_science.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>sbtf.cpp
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_remove_radar.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_debug.cpp
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_client_main.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>version.cpp
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>mtrand.cpp
1>dm_chunk_parallel.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_gfx_main.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Compiling with Intel(R) C++ 11.1.060 [IA-32]... (Intel C++ Environment)
1>ap_timer.cpp
1>-----USE_AVX activ-----
1>-----AVX undefined in x32, p8 used -----
1>Linking... (Intel C++ Environment)
1>xilink: executing 'link'
1>Embedding manifest... (Microsoft VC++ Environment)
1>AP SSE2_IPP_ICC_CSP_QaxSSE2_Qparallel_MKLP_BLANKIT_O2_Oi Win32 (Microsoft VC++ Environment)
1>Post Build revision number extraction
1>
1>APREV IS 374
1>Copy/Renaming Output Files
1>
1>Build log was saved at "file://C:\I\SC\apwk\ap_ICCIPP\client\WinBuild\ICC11_2k8\Win32\Output_ext\ap_client\AP_SSE2_CSP_QaxAVX\Intermediate\BuildLog.htm"
1>ap_client - 0 error(s), 0 warning(s)
========== Alles neu erstellen: 1 erfolgreich, Fehler bei 0, 0 übersprungen ==========
This is a build with dispatcher and include optimized code for the selected processor
from min SSE2 to SSE4.2
Its a Qax and run on any processor with SSE2 and above and Pentium3, and all Athlon with min SSE2
resultfile attached
A full 64Bit AVX build is in preparation ;)
[attachment deleted by admin]
_heinz:
Hi all,
update6 for parallel composer and ICSP is out. A lot todo with updates.
Composer update6
1>Compiling with Intel(R) C++ Compiler 11.1.082 [IA-32]... (Intel C++ Environment)
ICSP update6
1>Compiling with Intel(R) C++ 11.1.065 [IA-32]... (Intel C++ Environment)
thanks to all readers of this epic thread...
by the way, got "Brown Belt" from Intel today ;)
and 11 Mio today: 1st of Mai
Current Credit (based on incremental update) 11,016,471.91
regards
_heinz:
Hi,
the new driver 197.45 WHQL added Open CL 1.0 support to all devices upto Geforce 8 and later GPU's
Fügt Unterstützung für OpenCL(Open Computing Language) 1.0 für alle GeForce 8-Serie und später GPUs.
Version: 197.45 WHQL
Freigabedatum: 2010.04.13
Betriebssystem: Windows 7 64-bit
Sprache: Deutsch
Dateigröße: 143 MB
;)
http://www.nvidia.de/object/win7_winvista_64bit_197.45_whql_de.html
really great to get OCL this way ;D
_heinz:
And does it really worked you can see here:
~~~~~~~~~~~~~~~~~~~~~~~~~~
oclDeviceQuery.exe Starting...
OpenCL SW Info:
CL_PLATFORM_NAME: NVIDIA CUDA
CL_PLATFORM_VERSION: OpenCL 1.0 CUDA 3.0.1
OpenCL SDK Revision: 5537818
OpenCL Device Info:
1 devices found supporting OpenCL:
---------------------------------
Device ION
---------------------------------
CL_DEVICE_NAME: ION
CL_DEVICE_VENDOR: NVIDIA Corporation
CL_DRIVER_VERSION: 197.45
CL_DEVICE_TYPE: CL_DEVICE_TYPE_GPU
CL_DEVICE_MAX_COMPUTE_UNITS: 2
CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3
CL_DEVICE_MAX_WORK_ITEM_SIZES: 512 / 512 / 64
CL_DEVICE_MAX_WORK_GROUP_SIZE: 512
CL_DEVICE_MAX_CLOCK_FREQUENCY: 1100 MHz
CL_DEVICE_ADDRESS_BITS: 32
CL_DEVICE_MAX_MEM_ALLOC_SIZE: 128 MByte
CL_DEVICE_GLOBAL_MEM_SIZE: 241 MByte
CL_DEVICE_ERROR_CORRECTION_SUPPORT: no
CL_DEVICE_LOCAL_MEM_TYPE: local
CL_DEVICE_LOCAL_MEM_SIZE: 16 KByte
CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 64 KByte
CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_PROFILING_ENABLE
CL_DEVICE_IMAGE_SUPPORT: 1
CL_DEVICE_MAX_READ_IMAGE_ARGS: 128
CL_DEVICE_MAX_WRITE_IMAGE_ARGS: 8
CL_DEVICE_SINGLE_FP_CONFIG: INF-quietNaNs round-to-nearest round-to-
zero round-to-inf fma
CL_DEVICE_IMAGE <dim> 2D_MAX_WIDTH 8192
2D_MAX_HEIGHT 8192
3D_MAX_WIDTH 2048
3D_MAX_HEIGHT 2048
3D_MAX_DEPTH 2048
CL_DEVICE_EXTENSIONS: cl_khr_byte_addressable_store
cl_khr_icd
cl_khr_gl_sharing
cl_nv_d3d9_sharing
cl_nv_d3d10_sharing
cl_nv_d3d11_sharing
cl_nv_compiler_options
cl_nv_device_attribute_query
cl_nv_pragma_unroll
cl_khr_global_int32_base_atomics
cl_khr_global_int32_extended_atomics
CL_DEVICE_COMPUTE_CAPABILITY_NV: 1.1
NUMBER OF MULTIPROCESSORS: 2
NUMBER OF CUDA CORES: 16
CL_DEVICE_REGISTERS_PER_BLOCK_NV: 8192
CL_DEVICE_WARP_SIZE_NV: 32
CL_DEVICE_GPU_OVERLAP_NV: CL_FALSE
CL_DEVICE_KERNEL_EXEC_TIMEOUT_NV: CL_FALSE
CL_DEVICE_INTEGRATED_MEMORY_NV: CL_TRUE
CL_DEVICE_PREFERRED_VECTOR_WIDTH_<t> CHAR 1, SHORT 1, INT 1, LONG 1, FLOAT 1,
DOUBLE 0
oclDeviceQuery, Platform Name = NVIDIA CUDA, Platform Version = OpenCL 1.0 CUDA
3.0.1, SDK Revision = 5537818, NumDevs = 1, Device = ION
System Info:
Local Time/Date = 15:24:44, 5/26/2010
CPU Arch: 0
CPU Level: 6
# of CPU processors: 2
Windows Build: 6002
Windows Ver: 6.0
PASSED
Press <Enter> to Quit...
-----------------------------------------------------------
Navigation
[0] Message Index
[#] Next page
[*] Previous page
Go to full version