Microsoft MVP성태의 닷넷 이야기
글쓴 사람
정성태 (techsharer at outlook.com)
홈페이지
첨부 파일
 

(시리즈 글이 4개 있습니다.)
VC++: 125. CUDA로 작성한 RGB2RGBA 성능
; https://www.sysnet.pe.kr/2/0/11471

개발 환경 구성: 356. GTX 1070, GTX 960, GT 640M의 cudaGetDeviceProperties 출력 결과
; https://www.sysnet.pe.kr/2/0/11472

개발 환경 구성: 357. CUDA의 인덱싱 관련 용어 - blockIdx, threadIdx, blockDim, gridDim
; https://www.sysnet.pe.kr/2/0/11481

VC++: 126. CUDA Core 수를 알아내는 방법
; https://www.sysnet.pe.kr/2/0/11482




GTX 1070, GTX 960, GT 640M의 cudaGetDeviceProperties 출력 결과

그냥 기록 차원에서 남깁니다. ^^

우선, CUDA 사양을 cudaGetDeviceProperties API를 통해서 구하는 것이 가능하지만 CUDA SDK 설치 시 /extras/demo_suite 폴더의 deviceQuery.exe 프로그램을 이용하는 것이 편리합니다.

다음은, GTX 1070 시스템에서의 출력 결과이고,

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce GTX 1070"
  CUDA Driver Version / Runtime Version          9.1 / 9.1
  CUDA Capability Major/Minor version number:    6.1
  Total amount of global memory:                 8192 MBytes (8589934592 bytes)
  (15) Multiprocessors, (128) CUDA Cores/MP:     1920 CUDA Cores
  GPU Max Clock rate:                            1709 MHz (1.71 GHz)
  Memory Clock rate:                             4004 Mhz
  Memory Bus Width:                              256-bit
  L2 Cache Size:                                 2097152 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 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: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  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): (2147483647, 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:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  CUDA Device Driver Mode (TCC or WDDM):         WDDM (Windows Display Driver Model)
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.1, CUDA Runtime Version = 9.1, NumDevs = 1, Device0 = GeForce GTX 1070
Result = PASS

다음은 GTX 960,

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce GTX 960"
  CUDA Driver Version / Runtime Version          9.1 / 9.1
  CUDA Capability Major/Minor version number:    5.2
  Total amount of global memory:                 4096 MBytes (4294967296 bytes)
  ( 8) Multiprocessors, (128) CUDA Cores/MP:     1024 CUDA Cores
  GPU Max Clock rate:                            1291 MHz (1.29 GHz)
  Memory Clock rate:                             3505 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 1048576 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  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: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  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): (2147483647, 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:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  CUDA Device Driver Mode (TCC or WDDM):         WDDM (Windows Display Driver Model)
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.1, CUDA Runtime Version = 9.1, NumDevs = 1, Device0 = GeForce GTX 960
Result = PASS

다음은 GT 640M입니다.

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce GT 640M"
  CUDA Driver Version / Runtime Version          9.1 / 9.1
  CUDA Capability Major/Minor version number:    3.0
  Total amount of global memory:                 1024 MBytes (1073741824 bytes)
  ( 2) Multiprocessors, (192) CUDA Cores/MP:     384 CUDA Cores
  GPU Max Clock rate:                            709 MHz (0.71 GHz)
  Memory Clock rate:                             2000 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 262144 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  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: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  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): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 1 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  CUDA Device Driver Mode (TCC or WDDM):         WDDM (Windows Display Driver Model)
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.1, CUDA Runtime Version = 9.1, NumDevs = 1, Device0 = GeForce GT 640M
Result = PASS

참고로, Hyper-V의 RemoteFX 환경에서는 (당연하지만) 다음과 같이 CUDA 호환 장비를 찾을 수 없다는 메시지가 나옵니다.

 CUDA Device Query (Runtime API) version (CUDART static linking)

cudaGetDeviceCount returned 35
-> CUDA driver version is insufficient for CUDA runtime version
Result = FAIL




[이 글에 대해서 여러분들과 의견을 공유하고 싶습니다. 틀리거나 미흡한 부분 또는 의문 사항이 있으시면 언제든 댓글 남겨주십시오.]







[최초 등록일: ]
[최종 수정일: 3/22/2018]

Creative Commons License
이 저작물은 크리에이티브 커먼즈 코리아 저작자표시-비영리-변경금지 2.0 대한민국 라이센스에 따라 이용하실 수 있습니다.
by SeongTae Jeong, mailto:techsharer at outlook.com

비밀번호

댓글 작성자
 




... 166  167  168  169  170  171  172  173  174  175  176  177  178  179  [180]  ...
NoWriterDateCnt.TitleFile(s)
607정성태10/18/200825259Windows: 32. 자동 실행 경로에 ".." 가 포함된 경우
606정성태10/18/200827137.NET Framework: 106. WCF - 다중 서비스 호스트파일 다운로드1
605정성태10/18/200830310.NET Framework: 105. WPF - 닫기 버튼을 없애려면.
604정성태10/18/200830991오류 유형: 60. System.Management.ManagementException - Generic failure [1]
602정성태10/15/200833131오류 유형: 59. WPF - XAML 로딩 시 Visual Studio 비정상 종료 [1]
600정성태10/9/200838292디버깅 기술: 18. TFS Team Build + Source Server = 소스 코드 디버깅 [3]
603정성태10/15/200829481    답변글 디버깅 기술: 18.1. 소스 서버 구성, 그 외의 이야기
599정성태10/5/200834789디버깅 기술: 17. TFS Team Build + Symbol Server [1]
598정성태10/3/200825296VS.NET IDE: 57. VS.NET 2008 - 다중 프로젝트에서 단일 SNK를 사용하는 방법
597정성태10/2/200823648Team Foundation Server: 25. VSTS 2008의 Build Explorer
596정성태10/2/200830553오류 유형: 58. WPF : 드롭다운 유형의 ComboBox가 펼쳐지지 않는 문제
595정성태10/1/200838343디버깅 기술: 16. Watson Bucket 정보를 이용한 CLR 응용 프로그램 예외 분석 [2]
594정성태9/22/200826045.NET Framework: 104. Win32Exception 클래스 소개
591정성태7/24/200822614오류 유형: 57. VS.NET 2008 TFC - 체크인 시에 비프 음과 함께 정지되는 현상
592정성태7/28/200822244    답변글 오류 유형: 57.1. VS.NET 2008 TFC - 체크인 시에 비프 음과 함께 정지되는 현상 [1]
590정성태7/20/200828513.NET Framework: 103. WPF - ControlTemplate을 코드에서 다뤄보기 [1]
589정성태6/17/200825356.NET Framework: 102. COM 개체의 이벤트를 구독하는 코드 제작 [1]
588정성태6/13/200827610VC++: 35. COM 이벤트에서 반환값을 가진 콜백 정의
587정성태6/10/200831946VS.NET IDE: 56. C#에서 아쉬운 __DATE__, __TIME__ 매크로 [2]
586정성태6/4/200829673오류 유형: 56. WPF 디자이너 - The string was not recognized as a valid DateTime [2]
585정성태6/4/200837820.NET Framework: 101. WPF - ActiveX 컨트롤 호스팅하는 방법 [2]
582정성태5/16/200829795오류 유형: 55. Windowless ActiveX controls are not supported
580정성태4/24/200828773VC++: 34. 64비트 윈도우즈에서의 이벤트 후킹
579정성태4/24/200828486VC++: 33. 변환 후의 RGS 파일 내용을 얻는 방법
577정성태4/16/200829507.NET Framework: 100. XML Serializer를 이용한 값 복사 [5]
575정성태4/7/200826560오류 유형: 54. TFS Source Control - 명령을 사용할 수 없음 [2]
... 166  167  168  169  170  171  172  173  174  175  176  177  178  179  [180]  ...