NVIDIA CUDA parallel hisoblash texnologiyasi

CUDA
Скриншот программы CUDA
Turi GPGPU
Mualliflar Yan Bak
Jon Nikols
Ishlab chiquvchi Nvidia
Yozilgan dasturlash tili C
Operatsion tizimlar Windows, Linux
Chiqarilgan sana 16 fevral 2007; 19 yil avval (2007-02-16)
Uskuna platformasi Qo‘llab-quvvatlanadigan GPU’lar
Eng so‘nggi versiya 13.3.0 (26-may, 2026-yil)
Litsenziya Mulkiy (proprietar)
Veb-sayt developer.nvidia.com/… (inglizcha) — CUDA’ning rasmiy sayti
Логотип Викисклада Wikimedia Commons’dagi mediafayllar

CUDA (dastlab ingl. Compute Unified Device Architecture) — parallel hisoblashlar uchun mo‘ljallangan dasturiy-apparat arxitekturasi bo‘lib, u grafik protsessorlardan foydalanish orqali hisoblash unumdorligini sezilarli darajada oshiradi. Uni ishlab chiqqan kompaniya — Nvidia.

CUDA SDK dasturchilarga dasturlash tillarining maxsus soddalashtirilgan ko‘rinishlaridan foydalanib, C, C++ va Fortran tillarida Nvidia grafik va tenzor protsessorlarida bajariladigan algoritmlarni yaratish imkonini beradi. CUDA arxitekturasi ishlab chiquvchiga grafik yoki tenzor tezlatkichining ko‘rsatmalar to‘plamidan foydalanishni mustaqil tashkil etish va uning xotirasini boshqarish imkonini beradi. CUDA yordamida tezlashtirilgan funksiyalarni turli dasturlash tillaridan, jumladan Python, MATLAB va boshqalardan chaqirish mumkin.

Dasturiy arxitektura

CUDA — turli platformalarda ishlaydigan dasturiy ta’minot bo‘lib, u quyidagi operatsion tizimlarni qo‘llab-quvvatlaydi: Linux, Mac OS X va Windows. CUDA SDK’ning dastlabki versiyasi 15-fevral kuni , 2007-yilda taqdim etilgan. CUDA’ning ilovalarni dasturlash interfeysi asosida C tili va uning ayrim kengaytmalari yotadi. Ushbu tildagi kodni kompilyatsiya qilish uchun CUDA SDK tarkibiga Nvidia kompaniyasining buyruq qatorida ishlaydigan o‘z C kompilyatori — nvcc kiradi. nvcc kompilyatori ochiq kodli Open64 asosida yaratilgan bo‘lib, host-kod (asosiy, boshqaruvchi kod) va device-kodni (qurilmada bajariladigan kodni), ya’ni .cu kengaytmali fayllarni istalgan dasturlash muhitida yakuniy dastur yoki kutubxona yig‘ishda ishlatiladigan obyekt fayllarga aylantirish uchun mo‘ljallangan.

CUDA arxitekturasida grid xotira modeli, klasterlar bo‘yicha tashkil etilgan oqimlar va SIMD ko‘rsatmalaridan foydalaniladi. CUDA nafaqat yuqori unumli grafik hisoblashlarda, balki Nvidia videokartalari yordamida ilmiy hisoblashlarda ham qo‘llanadi. Olimlar va tadqiqotchilar CUDA’dan quyidagi sohalarda foydalanadilar: astrofizika, hisoblash biologiyasi va kimyo, suyuqliklar dinamikasini modellashtirish, elektromagnit o‘zaro ta’sirlar, kompyuter tomografiyasi, seysmik tahlil va boshqalar.

CUDA’da OpenGL va Direct3D bilan ishlaydigan ilovalarga ulanish imkoniyati mavjud. 22-mart kuni, 2010-yilda Nvidia CUDA Toolkit 3.0 versiyasini chiqarib, unga quyidagi texnologiyani qo‘llab-quvvatlash imkonini qo‘shdi: OpenCL.

Uskunalar

CUDA platformasi bozorda ilk bor sakkizinchi avlod Nvidia chipi G80 bilan birga paydo bo‘lgan va keyingi barcha grafik chiplar seriyalarida, jumladan quyidagi tezlatkich oilalarida qo‘llanilgan: GeForce, Quadro va Nvidia Tesla.

CUDA SDK’ni qo‘llab-quvvatlagan dastlabki G8x uskunalar seriyasida 32 bitli vektorli protsessor (bir aniqlikdagi) mavjud bo‘lgan va u CUDA SDK’dan API sifatida foydalangan (CUDA C tilidagi double turini qo‘llab-quvvatlaydi, ammo uning aniqligi hozir 32 bitli suzuvchi vergulli son darajasigacha pasaytirilgan). Keyingi GT200 protsessorlari 64 bitli aniqlikni (faqat SFU uchun) qo‘llab-quvvatlaydi, biroq bu rejimda unumdorlik 32 bitli aniqlikdagidan ancha past (sababi: har bir oqimli multiprotsessorda atigi ikkita SFU va sakkizta skalyar protsessor mavjud). Grafik protsessor barcha resurslardan foydalanish imkonini beradigan apparat darajasidagi ko‘p oqimlilikni tashkil etadi. Shu tariqa fizika tezlatkichi funksiyalarini grafik tezlatkichga yuklash imkoniyati paydo bo‘ladi (bunga PhysX misol bo‘la oladi). Kompyuterning grafik uskunalari murakkab, grafikaga aloqador bo‘lmagan hisoblashlarni bajarish uchun ham keng imkoniyatlar yaratadi, masalan, hisoblash biologiyasida.

Afzalliklari

Grafik API’lar imkoniyatlaridan foydalanib umumiy maqsadli hisoblashlarni tashkil etishning an’anaviy usuli bilan taqqoslanganda, CUDA arxitekturasining quyidagi afzalliklari qayd etiladi:

  • Ilovalarni dasturlash interfeysi CUDA (CUDA API) ayrim cheklovlarga ega standart C dasturlash tiliga asoslangan. Ishlab chiquvchilarning fikricha, bu CUDA arxitekturasini o‘rganishni osonlashtirishi va uning o‘zlashtirilishini soddalashtirishi kerak;
  • Oqimlar o‘rtasida taqsimlanadigan 16 KB hajmdagi xotiradan (shared memory) foydalanuvchi boshqaradigan kesh sifatida foydalanish mumkin. Bunday keshning o‘tkazish qobiliyati odatiy teksturalardan ma’lumot olishdagiga qaraganda yuqoriroq;
  • Markaziy protsessor xotirasi bilan videoxotira o‘rtasida samaraliroq ma’lumot almashish tranzaksiyalari;
  • Butun sonli va bitlar ustidagi amallarni apparat darajasida to‘liq qo‘llab-quvvatlash;
  • GPU kodini kompilyatsiya qilish uchun qo‘llab-quvvatlanadigan ochiq loyiha — LLVM.

Cheklovlari

  • Qurilmada bajariladigan barcha funksiyalar rekursiyani qo‘llab-quvvatlamaydi (CUDA Toolkit 3.1 versiyasida ko‘rsatkichlar va rekursiya qo‘llab-quvvatlanadi) va ayrim boshqa cheklovlarga ham ega.

Qo‘llab-quvvatlanadigan GPU’lar va grafik tezlatkichlar

CUDA texnologiyasini to‘liq qo‘llab-quvvatlashi e’lon qilingan Nvidia qurilmalari ro‘yxati kompaniyaning rasmiy saytida keltirilgan.

CUDA ishlab chiqish tizimlarining hisoblash qurilmalari avlodlari bilan mosligi:

  • CUDA SDK 6.0 1.0–3.5 versiyalarini qo‘llab-quvvatlaydi (Tesla, Fermi, Kepler).
  • CUDA SDK 6.5 1.0–5.x versiyalarini qo‘llab-quvvatlaydi (Tesla, Fermi, Kepler, Maxwell).
  • CUDA SDK 7.5 2.0–5.x versiyalarini qo‘llab-quvvatlaydi (Fermi, Kepler, Maxwell).
  • CUDA SDK 8.0 2.0–6.x versiyalarini qo‘llab-quvvatlaydi (Fermi, Kepler, Maxwell, Pascal).
  • CUDA SDK 9.0/9.1/9.2 3.0–7.2 versiyalarini qo‘llab-quvvatlaydi (Kepler, Maxwell, Pascal, Volta)
  • CUDA SDK 10.0 3.0–7.5 versiyalarini qo‘llab-quvvatlaydi (Kepler, Maxwell, Pascal, Volta, Turing)

Hozirgi vaqtda[qachon?] shaxsiy kompyuterlar uskunalari bozorida CUDA texnologiyasi quyidagi periferik qurilmalar tomonidan qo‘llab-quvvatlanadi:

Spetsifikatsiya

versiyasi

Arxitektura GPU GeForce oilasidagi videokartalar Quadro va NVS oilalaridagi videokartalar Tesla oilasidagi videokartalar Quyidagi oilalardagi videokartalar

Tegra,
Jetson,
DRIVE

1.0 Tesla G80 GeForce 8800 Ultra, GeForce 8800 GTX, GeForce 8800 GTS(G80) Quadro FX 5600, Quadro FX 4600, Quadro Plex 2100 S4 Tesla C870, Tesla D870, Tesla S870
1.1 G92, G94, G96, G98, G84, G86 GeForce GTS 250, GeForce 9800 GX2, GeForce 9800 GTX, GeForce 9800 GT, GeForce 8800 GTS(G92), GeForce 8800 GT, GeForce 9600 GT, GeForce 9500 GT, GeForce 9400 GT, GeForce 8600 GTS, GeForce 8600 GT, GeForce 8500 GT,
GeForce G110M, GeForce 9300M GS, GeForce 9200M GS, GeForce 9100M G, GeForce 8400M GT, GeForce G105M
Quadro FX 4700 X2, Quadro FX 3700, Quadro FX 1800, Quadro FX 1700, Quadro FX 580, Quadro FX 570, Quadro FX 470, Quadro FX 380, Quadro FX 370, Quadro FX 370 Low Profile, Quadro NVS 450, Quadro NVS 420, Quadro NVS 290, Quadro NVS 295, Quadro Plex 2100 D4,
Quadro FX 3800M, Quadro FX 3700M, Quadro FX 3600M, Quadro FX 2800M, Quadro FX 2700M, Quadro FX 1700M, Quadro FX 1600M, Quadro FX 770M, Quadro FX 570M, Quadro FX 370M, Quadro FX 360M, Quadro NVS 320M, Quadro NVS 160M, Quadro NVS 150M, Quadro NVS 140M, Quadro NVS 135M, Quadro NVS 130M, Quadro NVS 450, Quadro NVS 420, Quadro NVS 295
1.2 GT218, GT216, GT215 GeForce GT 340*, GeForce GT 330*, GeForce GT 320*, GeForce 315*, GeForce 310*, GeForce GT 240, GeForce GT 220, GeForce 210,
GeForce GTS 360M, GeForce GTS 350M, GeForce GT 335M, GeForce GT 330M, GeForce GT 325M, GeForce GT 240M, GeForce G210M, GeForce 310M, GeForce 305M
Quadro FX 380 Low Profile, Nvidia NVS 300, Quadro FX 1800M, Quadro FX 880M, Quadro FX 380M, Nvidia NVS 300, NVS 5100M, NVS 3100M, NVS 2100M, ION
1.3 GT200, GT200b GeForce GTX 295, GTX 285, GTX 280, GeForce GTX 275, GeForce GTX 260 Quadro FX 5800, Quadro FX 4800, Quadro FX 4800 for Mac, Quadro FX 3800, Quadro CX, Quadro Plex 2200 D2 Tesla C1060, Tesla S1070, Tesla M1060
2.0 Fermi GF100, GF110 GeForce GTX 590, GeForce GTX 580, GeForce GTX 570, GeForce GTX 480, GeForce GTX 470, GeForce GTX 465, GeForce GTX 480M Quadro 6000, Quadro 5000, Quadro 4000, Quadro 4000 for Mac, Quadro Plex 7000, Quadro 5010M, Quadro 5000M Tesla C2075, Tesla C2050/C2070, Tesla M2050/M2070/M2075/M2090
2.1 GF104, GF106 GF108, GF114, GF116, GF117, GF119 GeForce GTX 560 Ti, GeForce GTX 550 Ti, GeForce GTX 460, GeForce GTS 450, GeForce GTS 450*, GeForce GT 640 (GDDR3), GeForce GT 630, GeForce GT 620, GeForce GT 610, GeForce GT 520, GeForce GT 440, GeForce GT 440*, GeForce GT 430, GeForce GT 430*, GeForce GT 420*,
GeForce GTX 675M, GeForce GTX 670M, GeForce GT 635M, GeForce GT 630M, GeForce GT 625M, GeForce GT 720M, GeForce GT 620M, GeForce 710M, GeForce 610M, GeForce 820M, GeForce GTX 580M, GeForce GTX 570M, GeForce GTX 560M, GeForce GT 555M, GeForce GT 550M, GeForce GT 540M, GeForce GT 525M, GeForce GT 520MX, GeForce GT 520M, GeForce GTX 485M, GeForce GTX 470M, GeForce GTX 460M, GeForce GT 445M, GeForce GT 435M, GeForce GT 420M, GeForce GT 415M, GeForce 710M, GeForce 410M, GeForce GT 730 (DDR3 128-bit)
Quadro 2000, Quadro 2000D, Quadro 600, Quadro 410, Quadro 4000M, Quadro 3000M, Quadro 2000M, Quadro 1000M, NVS 310, NVS 315, NVS 5400M, NVS 5200M, NVS 4200M
3.0 Kepler GK104, GK106, GK107 GeForce GTX 770, GeForce GTX 760, GeForce GT 740, GeForce GTX 690, GeForce GTX 680, GeForce GTX 670, GeForce GTX 660 Ti, GeForce GTX 660, GeForce GTX 650 Ti BOOST, GeForce GTX 650 Ti, GeForce GTX 650,
GeForce GTX 880M, GeForce GTX 780M, GeForce GTX 770M, GeForce GTX 765M, GeForce GTX 760M, GeForce GTX 680MX, GeForce GTX 680M, GeForce GTX 675MX, GeForce GTX 670MX, GeForce GTX 660M, GeForce GT 750M, GeForce GT 650M, GeForce GT 745M, GeForce GT 645M, GeForce GT 740M, GeForce GT 730M, GeForce GT 640M, GeForce GT 640M LE, GeForce GT 735M, GeForce GT 730M
Quadro K5000, Quadro K4200, Quadro K4000, Quadro K2000, Quadro K2000D, Quadro K600, Quadro K500M, Quadro K510M, Quadro K610M, Quadro K1000M, Quadro K2000M, Quadro K1100M, Quadro K2100M, Quadro K3000M, Quadro K3100M, Quadro K4000M, Quadro K5000M, Quadro K4100M, Quadro K5100M, NVS 510 Tesla K10, GRID K340, GRID K520
3.2 GK20A Tegra K1,
Jetson TK1
3.5 GK110, GK208 GeForce GTX Titan Z, GeForce GTX Titan Black, GeForce GTX Titan, GeForce GTX 780 Ti, GeForce GTX 780, GeForce GT 640 (GDDR5), GeForce GT 630 v2, GeForce GT 730, GeForce GT 720, GeForce GT 710, GeForce GT 740M (64-bit, DDR3), GeForce GT 920M Quadro K6000, Quadro K5200 Tesla K40, Tesla K20x, Tesla K20
3.7 GK210 Tesla K80
5.0 Maxwell GM107, GM108 GeForce GTX 750 Ti, GeForce GTX 750, GeForce GTX 960M, GeForce GTX 950M, GeForce 940M, GeForce 930M, GeForce GTX 860M, GeForce GTX 850M, GeForce 845M, GeForce 840M, GeForce 830M Quadro K420, Quadro K620, Quadro K1200, Quadro K2200, Quadro M2000M, Quadro M1000M, Quadro M600M, Quadro K620M, NVS 810 Tesla M10
5.2 GM200, GM204, GM206 GeForce GTX Titan X, GeForce GTX 980 Ti, GeForce GTX 980, GeForce GTX 970, GeForce GTX 960, GeForce GTX 950, GeForce GTX 750 SE, GeForce GTX 980M, GeForce GTX 970M, GeForce GTX 965M Quadro M6000 24GB, Quadro M6000, Quadro M5000, Quadro M4000, Quadro M2000, Quadro M5500, Quadro M5000M, Quadro M4000M, Quadro M3000M Tesla M4, Tesla M40, Tesla M6, Tesla M60
5.3 GM20B Tegra X1,
Jetson TX1,
DRIVE CX,
DRIVE PX
6.0 Pascal GP100 Quadro GP100 Tesla P100
6.1 GP102, GP104, GP106, GP107, GP108 Nvidia TITAN Xp, Titan X, GeForce GTX 1080 Ti, GTX 1080, GTX 1070, GTX 1060, GTX 1050 Ti, GTX 1050, GT 1030, MX150 Quadro P6000, Quadro P5000, Quadro P4000, Quadro P2000, Quadro P1000, Quadro P600, Quadro P400, Quadro P5000(Mobile), Quadro P4000(Mobile), Quadro P3000(Mobile) Tesla P40, Tesla P6, Tesla P4
6.2 GP10B Drive PX2 with Tegra X2 (T186) Jetson TX2
7.0 Volta GV100 Nvidia TITAN V Quadro GV100 Tesla V100,

Tesla V100S

7.2 GV10B Jetson Xavier, DRIVE PX Xavier/Pegasus
Xavier bir kristalli tizimi (SoC) bilan
7.5 Turing TU102, TU104, TU106 NVIDIA TITAN RTX,

GeForce RTX 2080 Ti, RTX 2080 Super, RTX 2080, RTX 2070 Super, RTX 2070, RTX 2060 Super, RTX 2060,

GeForce GTX 1660 Ti, GTX 1660 Super, GTX 1660, GTX 1650 Super, GTX 1650

Quadro RTX 8000, Quadro RTX 6000, Quadro RTX 5000, Quadro RTX 4000, Quadro RTX 3000,

Quadro T2000, Quadro T1000, Quadro T600

Tesla T4
8.0 Ampere GA100 A100 80GB, A100 40GB
8.6 GA102, GA104, GA106, GA107 GeForce RTX 3090 Ti, RTX 3090, RTX 3080 Ti, RTX 3080, RTX 3070 Ti, RTX 3070, RTX 3060 Ti, RTX 3060, RTX 3050 Ti, RTX 3050 RTX A6000 A2, A10, A16, A40
8.9 Ada Lovelace AD102, AD103, AD104, AD106, AD107 GeForce RTX 4090, RTX 4080, RTX 4070 Ti, RTX 4070, RTX 4060 Ti, RTX 4060 RTX 6000 (Ada Generation) L40, L4
Stol kompyuterlari uchun Nvidia GeForce
GeForce GTX TITAN, X, Z, Black
GeForce RTX 4060/Ti, RTX 4070/Ti, RTX 4080, RTX 4090
GeForce RTX 3050, RTX 3060/Ti, RTX 3070/Ti,

RTX 3080/Ti, RTX 3090/Ti

GeForce RTX 2060/Super, RTX 2070/Super, RTX 2080/Super/Ti
GeForce GTX 1650/Super, GTX 1660/Super/Ti
GeForce GTX 1050/Ti, 1060, 1070, 1080/Ti
GeForce GTX 950, 960, 970, 980/Ti
GeForce GTX 750/Ti, 760, 770, 780/Ti
GeForce GTX 650/Ti, 660/Ti, 670, 680, 690
GeForce GTX 520, 550 Ti, 560/Ti, 570, 580, 590
GeForce GTX 450, 460, 465, 470, 480
GeForce GTX 210, 220, 240, 260, 275, 280, 285, 295
GeForce GT120, GT130, GTS 150
GeForce 9600 GSO, 9800 GTX, 9800 GTX+, 9800 GX2
GeForce 9400 GT, 9500 GT, 9600 GT, 9800 GT
GeForce 9300 mGPU, 9400 mGPU
GeForce 8800 GT, 8800 GTS 512
GeForce 8400 GS, 8500 GT, 8600 GT, 8600 GTS
Noutbuklar uchun Nvidia GeForce
GeForce GTX 580M
GeForce GTX 570M
GeForce GTX 560M
GeForce GT 555M
GeForce GT 540M
GeForce GT 525M
GeForce GT 520M
GeForce GTX 485M
GeForce GTX 480M
GeForce GTX 470M
GeForce GTX 460M
GeForce GT 445M
GeForce GT 435M
GeForce GT 425M
GeForce GT 420M
GeForce GT 415M
GeForce GTX 285M
GeForce GTX 280M
GeForce GTX 260M
GeForce GTS 360M
GeForce GTS 350M
GeForce GTS 250M
GeForce GTS 160M
GeForce GTS 150M
GeForce GT 335M
GeForce GT 330M
GeForce GT 325M
GeForce GT 240M
GeForce GT 130M
GeForce G210M
GeForce G110M
GeForce G105M
GeForce 310M
GeForce 305M
GeForce 9800M GTX
GeForce 9800M GT
GeForce 9800M GTS
GeForce 9700M GTS
GeForce 9700M GT
GeForce 9650M GS
GeForce 9600M GT
GeForce 9600M GS
GeForce 9500M GS
GeForce 9500M G
GeForce 9300M GS
GeForce 9300M G
GeForce 9200M GS
GeForce 9100M G
GeForce 8800M GTS
GeForce 8700M GT
GeForce 8600M GT
GeForce 8600M GS
GeForce 8400M GT
GeForce 8400M GS
Nvidia Tesla*
Tesla C2050/C2070
Tesla M2050/M2070/M2090
Tesla S2050
Tesla S1070
Tesla M1060
Tesla C1060
Tesla C870
Tesla D870
Tesla S870
Stol kompyuterlari uchun Nvidia Quadro
Quadro 6000
Quadro 5000
Quadro 4000
Quadro 2000
Quadro 600
Quadro FX 5800
Quadro FX 5600
Quadro FX 4800
Quadro FX 4700 X2
Quadro FX 4600
Quadro FX 3700
Quadro FX 1700
Quadro FX 570
Quadro FX 470
Quadro FX 380 Low Profile
Quadro FX 370
Quadro FX 370 Low Profile
Quadro CX
Quadro NVS 450
Quadro NVS 420
Quadro NVS 290
Quadro Plex 2100 D4
Quadro Plex 2200 D2
Quadro Plex 2100 S4
Quadro Plex 1000 Model IV
Noutbuklar uchun Nvidia Quadro
Quadro 5010M
Quadro 5000M
Quadro 4000M
Quadro 3000M
Quadro 2000M
Quadro 1000M
Quadro FX 3800M
Quadro FX 3700M
Quadro FX 3600M
Quadro FX 2800M
Quadro FX 2700M
Quadro FX 1800M
Quadro FX 1700M
Quadro FX 1600M
Quadro FX 880M
Quadro FX 770M
Quadro FX 570M
Quadro FX 380M
Quadro FX 370M
Quadro FX 360M
Quadro NVS 5100M
Quadro NVS 4200M
Quadro NVS 3100M
Quadro NVS 2100M
Quadro NVS 320M
Quadro NVS 160M
Quadro NVS 150M
Quadro NVS 140M
Quadro NVS 135M
Quadro NVS 130M
  • Tesla C1060, Tesla S1070, Tesla C2050/C2070, Tesla M2050/M2070 va Tesla S2050 modellari GPU’da ikki karra aniqlikdagi hisoblashlarni bajarish imkonini beradi.

Misol

Tasvirdagi teksturalarni C++ kodi yordamida massivga yuklashga misol. Hisoblash qurilmasi — GPU:

cudaArray* cu_array;
texture<float, 2> tex;

// Выделение памяти для массива
cudaMalloc( &cu_array, cudaCreateChannelDesc<float>(), width, height );

// Копируем данные изображения в массив
cudaMemcpy( cu_array, image, width*height, cudaMemcpyHostToDevice);

// Привязываем массив к текстуре
cudaBindTexture( tex, cu_array);

// Запускаем ядро
dim3 blockDim(16, 16, 1);
dim3 gridDim(width / blockDim.x, height / blockDim.y, 1);
kernel<<< gridDim, blockDim, 0 >>>(d_odata, width, height);
cudaUnbindTexture(tex);

__global__ void kernel(float* odata, int height, int width)
{
   unsigned int x = blockIdx.x*blockDim.x + threadIdx.x;
   unsigned int y = blockIdx.y*blockDim.y + threadIdx.y;
   float c = texfetch(tex, x, y);
   odata[y*width+x] = c;
}

GPU yordamida massiv elementlarini o‘zaro ko‘paytiradigan Python dasturiga misol keltirilgan. GPU bilan o‘zaro aloqa PyCUDA orqali amalga oshiriladi.

import pycuda.driver as drv
import numpy

drv.init()
dev = drv.Device(0)
ctx = dev.make_context()

mod = drv.SourceModule("""
__global__ void multiply_them(float *dest, float *a, float *b)
{
  const int i = threadIdx.x;
  dest[i] = a[i] * b[i];
}
""")

multiply_them = mod.get_function("multiply_them")

a = numpy.random.randn(400).astype(numpy.float32)
b = numpy.random.randn(400).astype(numpy.float32)

dest = numpy.zeros_like(a)
multiply_them(
        drv.Out(dest), drv.In(a), drv.In(b),
        block=(400,1,1))

print dest-a*b

Havolalar

Rasmiy manbalar

Norasmiy manbalar

Tom's Hardware

iXBT.com

Boshqa manbalar