'프로그램 사용 > VLC' 카테고리의 다른 글
| VLC RTSP 데이터 덤프하기? (0) | 2013.02.26 |
|---|---|
| vlc를 이용한 html rtsp 스트리밍 예제 (2) | 2013.01.11 |
| VLC codebase axvlc.cab (2) | 2011.11.18 |
| VLC classid (0) | 2011.11.18 |
| VLC로 웹상에서 RTSP 비디오 띄우기 (0) | 2011.11.17 |
| VLC RTSP 데이터 덤프하기? (0) | 2013.02.26 |
|---|---|
| vlc를 이용한 html rtsp 스트리밍 예제 (2) | 2013.01.11 |
| VLC codebase axvlc.cab (2) | 2011.11.18 |
| VLC classid (0) | 2011.11.18 |
| VLC로 웹상에서 RTSP 비디오 띄우기 (0) | 2011.11.17 |
| 5.2 Maximize Utilization 5.2.3 Multiprocessor Level If all input operands are registers, latency is caused by register dependencies, i.e. some of the input operands are written by some previous instruction(s) whose execution has not completed yet. In the case of a back-to-back register dependency (i.e. some input operand is written by the previous instruction), the latency is equal to the execution time of the previous instruction and the warp schedulers must schedule instructions for different warps during that time. Execution time varies depending on the instruction, but it is typically about 22 clock cycles for devices of compute capability 1.x and 2.x and about 11 clock cycles for devices of compute capability 3.0, which translates to 6 warps for devices of compute capability 1.x and 22 warps for devices of compute capability 2.x and higher (still assuming that warps execute instructions with maximum throughput, otherwise fewer warps are needed). For devices of compute capability 2.1 and higher, this is also assuming enough instruction-level parallelism so that schedulers are always able to issue pairs of instructions for each warp. If some input operand resides in off-chip memory, the latency is much higher: 400 to 800 clock cycles. The number of warps required to keep the warp schedulers busy during such high latency periods depends on the kernel code and its degree of instruction-level parallelism. In general, more warps are required if the ratio of the number of instructions with no off-chip memory operands (i.e. arithmetic instructions most of the time) to the number of instructions with off-chip memory operands is low (this ratio is commonly called the arithmetic intensity of the program). If this ratio is 15, for example, then to hide latencies of about 600 clock cycles, about 10 warps are required for devices of compute capability 1.x and about 40 for devices of compute capability 2.x and higher (with the same assumptions as in the previous paragraph).
5.3
Maximize Memory Throughput
The first step in maximizing overall memory throughput for the application is to minimize data transfers with low bandwidth.
That means minimizing data transfers between the host and the device, as detailed in Section 5.3.1, since these have much lower bandwidth than data transfers between global memory and the device.
That also means minimizing data transfers between global memory and the device by maximizing use of on-chip memory: shared memory and caches (i.e. L1/L2 caches available on devices of compute capability 2.x and higher, texture cache and constant cache available on all devices).
|
| cuda 에서 device memory의 용량을 초과하는 malloc은 위험해! (0) | 2012.06.06 |
|---|---|
| nvcc 는 int main()을 좋아해 (0) | 2012.06.05 |
| ubuntu 에서 vectorAdd 직접 컴파일 하기 (0) | 2012.06.03 |
| CUDA devicequery - ION 330 (0) | 2012.06.02 |
| cuda 5 preview (0) | 2012.06.02 |
| USB to RS232 컨버터 데이터 수신 몇바이트 놓칠경우 (2) | 2012.11.06 |
|---|---|
| LTE vs WIFI(802.11n) (0) | 2012.11.02 |
| 2T2R이 머여? (2) | 2012.02.07 |
| IEEE 1394 속도 벤치마크 관련문서들 (0) | 2011.12.13 |
| iptime VPN 설정 (0) | 2011.12.06 |
| vectorAdd.cu:24:82: fatal error: sdkHelper.h: 그런 파일이나 디렉터리가 없습니다
vectorAdd.cu:25:23: fatal error: shrQATest.h: 그런 파일이나 디렉터리가 없습니다
|
| $ /usr/local/cuda/bin/nvcc vectorAdd.cu \ -I/home/minimonk/NVIDIA_GPU_Computing_SDK/C/common/inc \ -I/home/minimonk/NVIDIA_GPU_Computing_SDK/shared/inc |
~/NVIDIA_GPU_Computing_SDK/C/common/inc$ ll
합계 572
drwxrwxr-x 4 minimonk minimonk 4096 6월 2 19:00 ./
drwxrwxr-x 6 minimonk minimonk 4096 6월 2 20:25 ../
drwxrwxr-x 2 minimonk minimonk 4096 6월 2 19:00 GL/
-rw-rw-r-- 1 minimonk minimonk 14391 6월 2 19:00 bank_checker.h
-rw-rw-r-- 1 minimonk minimonk 15841 6월 2 19:00 cmd_arg_reader.h
-rw-rw-r-- 1 minimonk minimonk 3999 6월 2 19:00 cudaGLHelper.h
-rw-rw-r-- 1 minimonk minimonk 6442 6월 2 19:00 cudaHelper.h
-rw-rw-r-- 1 minimonk minimonk 20787 6월 2 19:00 cuda_drvapi_dynlink.c
-rw-rw-r-- 1 minimonk minimonk 46935 6월 2 19:00 cutil.h
-rw-rw-r-- 1 minimonk minimonk 3183 6월 2 19:00 cutil_gl_error.h
-rw-rw-r-- 1 minimonk minimonk 3492 6월 2 19:00 cutil_gl_inline.h
-rw-rw-r-- 1 minimonk minimonk 1116 6월 2 19:00 cutil_inline.h
-rw-rw-r-- 1 minimonk minimonk 953 6월 2 19:00 cutil_inline_bankchecker.h
-rw-rw-r-- 1 minimonk minimonk 13007 6월 2 19:00 cutil_inline_drvapi.h
-rw-rw-r-- 1 minimonk minimonk 17779 6월 2 19:00 cutil_inline_runtime.h
-rw-rw-r-- 1 minimonk minimonk 36730 6월 2 19:00 cutil_math.h
-rw-rw-r-- 1 minimonk minimonk 10864 6월 2 19:00 drvapi_error_string.h
drwxrwxr-x 2 minimonk minimonk 4096 6월 2 19:00 dynlink/
-rw-rw-r-- 1 minimonk minimonk 15321 6월 2 19:00 dynlink_d3d10.h
-rw-rw-r-- 1 minimonk minimonk 6202 6월 2 19:00 dynlink_d3d11.h
-rw-rw-r-- 1 minimonk minimonk 1809 6월 2 19:00 error_checker.h
-rw-rw-r-- 1 minimonk minimonk 5035 6월 2 19:00 exception.h
-rw-rw-r-- 1 minimonk minimonk 26819 6월 2 19:00 helper_cuda.h
-rw-rw-r-- 1 minimonk minimonk 5973 6월 2 19:00 helper_cuda_drvapi.h
-rw-rw-r-- 1 minimonk minimonk 4151 6월 2 19:00 helper_cuda_gl.h
-rw-rw-r-- 1 minimonk minimonk 1132 6월 2 19:00 helper_functions.h
-rw-rw-r-- 1 minimonk minimonk 22291 6월 2 19:00 helper_image.h
-rw-rw-r-- 1 minimonk minimonk 10491 6월 2 19:00 helper_string.h
-rw-rw-r-- 1 minimonk minimonk 15757 6월 2 19:00 helper_timer.h
-rw-rw-r-- 1 minimonk minimonk 1323 6월 2 19:00 multithreading.h
-rw-rw-r-- 1 minimonk minimonk 7228 6월 2 19:00 nvGLWidgets.h
-rw-rw-r-- 1 minimonk minimonk 4646 6월 2 19:00 nvGlutWidgets.h
-rw-rw-r-- 1 minimonk minimonk 2967 6월 2 19:00 nvMath.h
-rw-rw-r-- 1 minimonk minimonk 10850 6월 2 19:00 nvMatrix.h
-rw-rw-r-- 1 minimonk minimonk 12347 6월 2 19:00 nvQuaternion.h
-rw-rw-r-- 1 minimonk minimonk 6415 6월 2 19:00 nvShaderUtils.h
-rw-rw-r-- 1 minimonk minimonk 20642 6월 2 19:00 nvVector.h
-rw-rw-r-- 1 minimonk minimonk 15917 6월 2 19:00 nvWidgets.h
-rw-rw-r-- 1 minimonk minimonk 5309 6월 2 19:00 param.h
-rw-rw-r-- 1 minimonk minimonk 2321 6월 2 19:00 paramgl.h
-rw-rw-r-- 1 minimonk minimonk 1024 6월 2 19:00 rendercheck_d3d10.h
-rw-rw-r-- 1 minimonk minimonk 1027 6월 2 19:00 rendercheck_d3d11.h
-rw-rw-r-- 1 minimonk minimonk 998 6월 2 19:00 rendercheck_d3d9.h
-rw-rw-r-- 1 minimonk minimonk 7662 6월 2 19:00 rendercheck_gl.h
-rw-rw-r-- 1 minimonk minimonk 26682 6월 2 19:00 sdkHelper.h
-rw-rw-r-- 1 minimonk minimonk 1116 6월 2 19:00 stopwatch.h
-rw-rw-r-- 1 minimonk minimonk 1897 6월 2 19:00 stopwatch_base.h
-rw-rw-r-- 1 minimonk minimonk 2804 6월 2 19:00 stopwatch_base.inl
-rw-rw-r-- 1 minimonk minimonk 11608 6월 2 19:00 stopwatch_functions.h
-rw-rw-r-- 1 minimonk minimonk 4647 6월 2 19:00 stopwatch_linux.h
-rw-rw-r-- 1 minimonk minimonk 9342 6월 2 19:00 string_helper.h
|
| ~/NVIDIA_GPU_Computing_SDK/shared/inc$ ll
합계 192
drwxrwxr-x 4 minimonk minimonk 4096 6월 2 19:00 ./
drwxrwxr-x 6 minimonk minimonk 4096 6월 2 20:25 ../
drwxrwxr-x 2 minimonk minimonk 4096 6월 2 19:00 GL/
-rw-rw-r-- 1 minimonk minimonk 15439 6월 2 19:00 cmd_arg_reader.h
drwxrwxr-x 2 minimonk minimonk 4096 6월 2 19:00 dynlink/
-rw-rw-r-- 1 minimonk minimonk 5035 6월 2 19:00 exception.h
-rw-rw-r-- 1 minimonk minimonk 1323 6월 2 19:00 multithreading.h
-rw-rw-r-- 1 minimonk minimonk 7228 6월 2 19:00 nvGLWidgets.h
-rw-rw-r-- 1 minimonk minimonk 4646 6월 2 19:00 nvGlutWidgets.h
-rw-rw-r-- 1 minimonk minimonk 2966 6월 2 19:00 nvMath.h
-rw-rw-r-- 1 minimonk minimonk 10850 6월 2 19:00 nvMatrix.h
-rw-rw-r-- 1 minimonk minimonk 12347 6월 2 19:00 nvQuaternion.h
-rw-rw-r-- 1 minimonk minimonk 6108 6월 2 19:00 nvShaderUtils.h
-rw-rw-r-- 1 minimonk minimonk 20642 6월 2 19:00 nvVector.h
-rw-rw-r-- 1 minimonk minimonk 15917 6월 2 19:00 nvWidgets.h
-rw-rw-r-- 1 minimonk minimonk 8092 6월 2 19:00 rendercheckGL.h
-rw-rw-r-- 1 minimonk minimonk 6801 6월 2 19:00 shrQATest.h
-rw-rw-r-- 1 minimonk minimonk 33202 6월 2 19:00 shrUtils.h |
| /usr/local/cuda/lib$ ll
합계 394240
drwxr-xr-x 2 root root 4096 6월 2 18:47 ./
drwxr-xr-x 12 root root 4096 6월 2 18:47 ../
lrwxrwxrwx 1 root root 14 6월 2 18:46 libcublas.so -> libcublas.so.4*
lrwxrwxrwx 1 root root 18 6월 2 18:47 libcublas.so.4 -> libcublas.so.4.2.9*
-rwxr-xr-x 1 root root 105568932 6월 2 18:46 libcublas.so.4.2.9*
lrwxrwxrwx 1 root root 14 6월 2 18:46 libcudart.so -> libcudart.so.4*
lrwxrwxrwx 1 root root 18 6월 2 18:47 libcudart.so.4 -> libcudart.so.4.2.9*
-rwxr-xr-x 1 root root 427344 6월 2 18:46 libcudart.so.4.2.9*
lrwxrwxrwx 1 root root 13 6월 2 18:47 libcufft.so -> libcufft.so.4*
lrwxrwxrwx 1 root root 17 6월 2 18:46 libcufft.so.4 -> libcufft.so.4.2.9*
-rwxr-xr-x 1 root root 29333272 6월 2 18:47 libcufft.so.4.2.9*
lrwxrwxrwx 1 root root 13 6월 2 18:46 libcuinj.so -> libcuinj.so.4*
lrwxrwxrwx 1 root root 17 6월 2 18:46 libcuinj.so.4 -> libcuinj.so.4.2.9*
-rwxr-xr-x 1 root root 157120 6월 2 18:46 libcuinj.so.4.2.9*
lrwxrwxrwx 1 root root 14 6월 2 18:46 libcurand.so -> libcurand.so.4*
lrwxrwxrwx 1 root root 18 6월 2 18:46 libcurand.so.4 -> libcurand.so.4.2.9*
-rwxr-xr-x 1 root root 27434820 6월 2 18:47 libcurand.so.4.2.9*
lrwxrwxrwx 1 root root 16 6월 2 18:46 libcusparse.so -> libcusparse.so.4*
lrwxrwxrwx 1 root root 20 6월 2 18:46 libcusparse.so.4 -> libcusparse.so.4.2.9*
-rwxr-xr-x 1 root root 188374460 6월 2 18:47 libcusparse.so.4.2.9*
lrwxrwxrwx 1 root root 11 6월 2 18:46 libnpp.so -> libnpp.so.4*
lrwxrwxrwx 1 root root 15 6월 2 18:46 libnpp.so.4 -> libnpp.so.4.2.9*
-rwxr-xr-x 1 root root 52381048 6월 2 18:46 libnpp.so.4.2.9* |
| nvcc 는 int main()을 좋아해 (0) | 2012.06.05 |
|---|---|
| cuda 메모리별 접근 소요 클럭 사이클 (0) | 2012.06.05 |
| CUDA devicequery - ION 330 (0) | 2012.06.02 |
| cuda 5 preview (0) | 2012.06.02 |
| nvidia ion cuda core와 h.264 library (0) | 2012.05.22 |
| $ sudo apt-get install phpmyadmin |
| phpmyadmn에서 뷰 생성하기? (0) | 2017.04.07 |
|---|---|
| mysql foreign key와 internal relation(phpmyadmin) (0) | 2017.01.04 |
| mysql table auto_increment 와 not null (0) | 2017.01.04 |
| phpmyadmin에서 blob 데이터 보기 (0) | 2014.07.16 |
| 우분투에서 phpmyadmin 패키지 설치 후 접속되지 않는 문제 (0) | 2013.02.22 |
시리얼 / 패러럴이 없는게 아쉽지만 추세이니 어쩔수 없고
HDMI / DVI / D-SUB 세가지에 좀 계륵이지만 PS/2 포트를 지원한다.
표준형 어댑터 크기라서 교체하기도 용이할 듯.
단, 12V / 5A 짜리라서 용량이 큰지라 구하기는 좀 쉽지 않을 듯 하다.
안에는 이렇게 깔끔하게 생겼고, CPU는 fanless 모델로
본체에 1개의 팬으로 플라스틱 덕트를 통해 강제 배기 시키는 구조이다.
전원스위치는 저런식으로 달려있고, 전원 들어 오면 흰색(밤에는 좀 밝네 ㅠ.ㅠ)
HDD 작동시에는 빨간불이 들어온다.
전원 켜면 이렇게 아이언맨 아크원자로 처럼 흰색 불이 뽀대나게!
HDD 읽을때는 빨간색이 들어오는데 이러니까 악당꺼 같다?
사양은 DDR2 2GB
Atom 330 dual core / HT(끄는 옵션은 못 찾음)
320GB 2.5인치 하드
대기전력은 1W 정도
BIOS에서 24W 최대 30W 정도까지 올라간다.
현재 우분투 12.04 LTS 에 ssh 만 깔아놓고 cuda 설정해놓고 가지고 놀기 대기중 ㅋㅋㅋ
| 업어온 컴퓨터 (0) | 2012.08.19 |
|---|---|
| umid mbook m1 충전시간 (0) | 2012.07.03 |
| 아직은 너무나 먼 리눅스 (0) | 2012.06.03 |
| 아 몰라 지르고 봐! (2) | 2012.05.31 |
| 욕심 / 목표 / 폭파 (0) | 2012.05.28 |
| umid mbook m1 충전시간 (0) | 2012.07.03 |
|---|---|
| ripple look ion 330 모델 (0) | 2012.06.03 |
| 아 몰라 지르고 봐! (2) | 2012.05.31 |
| 욕심 / 목표 / 폭파 (0) | 2012.05.28 |
| 아 지르고 싶다 ㅠ.ㅠ (0) | 2012.05.26 |
| $ gcc -lglut -lGLU -lGL |
| openGL state variables (0) | 2013.12.12 |
|---|---|
| openGL에서 AVI 동영상 재생하기 (0) | 2013.04.09 |
| glsl과 glew의 연관관계 (0) | 2011.11.22 |
| GLSL 관련 링크 (0) | 2011.11.20 |
| GLSL 함수목록 정리 (0) | 2011.11.20 |
| $ cat /etc/X11/xorg.conf
# nvidia-settings: X configuration file generated by nvidia-settings
# nvidia-settings: version 295.33 (buildd@zirconium) Fri Mar 30 13:38:49 UTC 2012
Section "ServerLayout"
Identifier "Layout0"
Screen 0 "Screen0" 0 0
InputDevice "Keyboard0" "CoreKeyboard"
InputDevice "Mouse0" "CorePointer"
Option "Xinerama" "0"
EndSection
Section "Files"
EndSection
Section "InputDevice"
# generated from default
Identifier "Mouse0"
Driver "mouse"
Option "Protocol" "auto"
Option "Device" "/dev/psaux"
Option "Emulate3Buttons" "no"
Option "ZAxisMapping" "4 5"
EndSection
Section "InputDevice"
# generated from default
Identifier "Keyboard0"
Driver "kbd"
EndSection
Section "Monitor"
# HorizSync source: edid, VertRefresh source: edid
Identifier "Monitor0"
VendorName "Unknown"
ModelName "Budzetron ANALOG"
HorizSync 30.0 - 80.0
VertRefresh 50.0 - 75.0
Option "DPMS"
EndSection
Section "Device"
Identifier "Device0"
Driver "nvidia"
VendorName "NVIDIA Corporation"
BoardName "ION"
EndSection
Section "Screen"
Identifier "Screen0"
Device "Device0"
Monitor "Monitor0"
DefaultDepth 24
Option "TwinView" "0"
Option "metamodes" "1280x1024_60 +0+0"
Option "ConnectedMonitor" "CRT-0"
Option "UseDisplayDevice" "CRT-0"
SubSection "Display"
Depth 24
Modes "1280x1024"
EndSubSection
EndSection
|
| 우분투 자동 마운트(외장 USB HDD)시 700 퍼미션 문제 (2) | 2012.06.07 |
|---|---|
| rutorrent on ubuntu 12.04 LTS (0) | 2012.06.07 |
| cannot open shared object file: No such file or directory (1) | 2012.06.02 |
| cuda 4.2 linux (0) | 2012.06.02 |
| grub loader 날리기 (0) | 2012.04.29 |
| ~/NVIDIA_GPU_Computing_SDK/C/bin/linux/release$ ./deviceQuery
[deviceQuery] starting...
./deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Found 1 CUDA Capable device(s)
Device 0: "ION"
CUDA Driver Version / Runtime Version 4.2 / 4.2
CUDA Capability Major/Minor version number: 1.1
Total amount of global memory: 254 MBytes (266010624 bytes)
( 2) Multiprocessors x ( 8) CUDA Cores/MP: 16 CUDA Cores
GPU Clock rate: 1100 MHz (1.10 GHz)
Memory Clock rate: 800 Mhz
Memory Bus Width: 64-bit
Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)
Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 8192
Warp size: 32
Maximum number of threads per multiprocessor: 768
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch: 2147483647 bytes
Texture alignment: 256 bytes
Concurrent copy and execution: No with 0 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: Yes
Support host page-locked memory mapping: Yes
Concurrent kernel execution: No
Alignment requirement for Surfaces: Yes
Device has ECC support enabled: No
Device is using TCC driver mode: No
Device supports Unified Addressing (UVA): No
Device PCI Bus ID / PCI location ID: 3 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.2, CUDA Runtime Version = 4.2, NumDevs = 1, Device = ION
[deviceQuery] test results...
PASSED
> exiting in 3 seconds:
3...2...1...done! |
| ~/NVIDIA_GPU_Computing_SDK/C/bin/linux/release$ ./bandwidthTest
[bandwidthTest] starting...
./bandwidthTest Starting...
Running on...
Device 0: ION
Quick Mode
Host to Device Bandwidth, 1 Device(s), Paged memory
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 887.0
Device to Host Bandwidth, 1 Device(s), Paged memory
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 735.9
Device to Device Bandwidth, 1 Device(s)
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 5345.2
[bandwidthTest] test results...
PASSED
|
| $ cat /proc/driver/nvidia/version
NVRM version: NVIDIA UNIX x86 Kernel Module 295.40 Thu Apr 5 21:28:09 PDT 2012
GCC version: gcc version 4.6.3 (Ubuntu/Linaro 4.6.3-1ubuntu5)
|
| cuda 메모리별 접근 소요 클럭 사이클 (0) | 2012.06.05 |
|---|---|
| ubuntu 에서 vectorAdd 직접 컴파일 하기 (0) | 2012.06.03 |
| cuda 5 preview (0) | 2012.06.02 |
| nvidia ion cuda core와 h.264 library (0) | 2012.05.22 |
| CUDA API 메모리 종류 (0) | 2012.05.18 |