cuda9.0支持的显卡
为大家整理了一份官方提供CUDA支持显卡清单。NVIDIA NVS 810 5.0NVIDIA NVS 510 3.0
NVIDIA NVS 315 2.1
NVIDIA NVS 310 2.1
NVIDIA A100 8.0
NVIDIA A40 8.6
NVIDIA A30 8.0
NVIDIA A10 8.6
NVIDIA A16 8.6
NVIDIA A2 8.6
NVIDIA T4 7.5
NVIDIA V100 7.0
Tesla P100 6.0
Tesla P40 6.1
Tesla P4 6.1
Tesla M60 5.2
Tesla M40 5.2
Tesla K80 3.7
Tesla K40 3.5
Tesla K20 3.5
Tesla K10 3.0
RTX A6000 8.6
RTX A5000 8.6
RTX A4000 8.6
T1000 7.5
T600 7.5
T400 7.5
Quadro RTX 8000 7.5
Quadro RTX 6000 7.5
Quadro RTX 5000 7.5
Quadro RTX 4000 7.5
Quadro GV100 7.0
Quadro GP100 6.0
Quadro P6000 6.1
Quadro P5000 6.1
Quadro P4000 6.1
Quadro P2200 6.1
Quadro P2000 6.1
Quadro P1000 6.1
Quadro P620 6.1
Quadro P600 6.1
Quadro P400 6.1
Quadro M6000 24GB 5.2
Quadro M6000 5.2
Quadro K6000 3.5
Quadro M5000 5.2
Quadro K5200 3.5
Quadro K5000 3.0
Quadro M4000 5.2
Quadro K4200 3.0
Quadro K4000 3.0
Quadro M2000 5.2
Quadro K2200 5.0
Quadro K2000 3.0
Quadro K2000D 3.0
Quadro K1200 5.0
Quadro K620 5.0
Quadro K600 3.0
Quadro K420 3.0
Quadro 410 3.0
Quadro Plex 7000 2.0
RTX A5000 8.6
RTX A4000 8.6
RTX A3000 8.6
RTX A2000 8.6
RTX 5000 7.5
RTX 4000 7.5
RTX 3000 7.5
T2000 7.5
T1200 7.5
T1000 7.5
T600 7.5
T500 7.5
P620 6.1
P520 6.1
Quadro P5200 6.1
Quadro P4200 6.1
Quadro P3200 6.1
Quadro P5000 6.1
Quadro P4000 6.1
Quadro P3000
可以在2080上装cuda9.0匹配torch0.4.0，程序也能跑，但是训练的时候老是有warning，不如在v100上流畅。torch0.4.0版本的程序可以在torch1.0的环境下跑效果会不好。
绛旓細涓哄ぇ瀹舵暣鐞嗕簡涓浠藉畼鏂规彁渚CUDA鏀寔鏄惧崱娓呭崟銆侼VIDIA NVS 8105.0 NVIDIA NVS 5103.0 NVIDIA NVS 3152.1 NVIDIA NVS 3102.1 NVIDIA A1008.0 NVIDIA A408.6 NVIDIA A308.0 NVIDIA A108.6 NVIDIA A168.6 NVIDIA A28.6 NVIDIA T47.5 NVIDIA V1007.0 Tesla P1006.0 Tesla P406.1 Tesla P46.1...
绛旓細NVIDIA鐨凙D104GPU浣跨敤Lovelace鏋舵瀯锛屽苟浣跨敤鍙扮Н鐢电殑5绾崇背鐢熶骇宸ヨ壓鍒堕犮傚畠鐨勮姱鐗囧昂瀵镐负300mm²锛屾槸涓涓ぇ鑺墖銆侫D104鏀寔DirectX12Ultimate锛堝姛鑳界骇鍒12_2锛夈傚浜嶨PU璁＄畻搴旂敤绋嬪簭锛屽彲浠ヤ娇鐢∣penCL鐗堟湰3.0鍜CUDA9.0銆鏄惧崱鐨勪綔鐢細鏄惧崱鐨勪富瑕佷綔鐢ㄦ槸灏咰PU鎻愪緵鐨勬寚浠ゅ拰鏁版嵁杩涜鐩稿簲鐨勫鐞嗗彉鎴愭樉绀哄櫒鑳藉鎺...
绛旓細CUDA 9.0鐨TMA锛圱ensor Memory Accelerator锛変綔涓篠M鍐呴儴鐨勬柊鎴愬憳锛屽紩鍏ヤ簡寰瀷DMA鎺у埗鍣紝鐩存帴浠巊lobal memory楂樻晥浼犺緭鏁版嵁鍒皊hared memory锛屾棤闇缁忚繃绻佺悙鐨勫瘎瀛樺櫒姝ラ锛屾瀬澶у湴鎻愰珮浜嗘暟鎹鐞嗘晥鐜囥備笌浼犵粺寮傛鍔犺浇鐩告瘮锛孴MA鎻愪緵浜嗘洿楂樻晥鐨勫潡浼犺緭锛鏀寔瀹藉害銆乻tride涓嶄竴鑷村拰杈圭晫澶勭悊锛屽噺杞讳簡SM鍐呴儴鍗曞厓鐨勫伐浣滆礋鎷咃紝...
绛旓細缁煎悎浠ヤ笂鍒嗘瀽锛孏TX3090闇瑕丆ompute Capability鍦8.6浠ヤ笂鐨刢uda锛岃屾弧瓒宠繖涓姹傜殑cuda鍙堝彧鏈11.0浠ヤ笂鐨勭増鏈傝宑uda11鐗堟湰鍙堥渶瑕佺増鏈彿>450鐨勬樉鍗椹卞姩銆傚叾瀹烇紝浠庤〃涓垜浠篃鍙互鍒嗘瀽鍑猴紝cuda鍜屾樉鍗￠┍鍔ㄥ熀鏈兘鏄悜涓嬪吋瀹圭殑锛屾剰鍛崇潃鎴戝畨瑁呮渶鏂扮殑cuda鍜屾樉鍗￠┍鍔紝鍩烘湰涓婂彲浠鏀寔浠ュ墠鐨勫嚑涔庢墍鏈夋樉鍗°傚綋鐒朵簡锛屼唬浠...
绛旓細璇鏄惧崱鏀寔DirectX 11銆CUDA銆丳hysX銆3D Vision浠ュ強Optimus鎶鏈備篃鏈夌殑鏍囬厤2G鐨勬樉瀛樸傚疄鍐2012鏈浣庨厤缃細鏄惧崱锛氬吋瀹笵X9.0c銆128MB鏄惧瓨锛孏eForce FX/Radeon 9700鎴栨洿濂 鎺ㄨ崘閰嶇疆锛氭樉鍗★細鍏煎DX9.0c銆256MB鏄惧瓨锛孏eForce 7900/Radeon HD 2400鎴栨洿濂 鎵浠ユ垜瑙夊緱寰堟甯革紝浣犺繖涓湰鏉ュ氨鍙揪鍒颁簡鏈浣庨厤缃紝...
绛旓細涓昏鐜╂父鎴忕殑璇濓紝CUDA鎰忎箟涓嶆槸鐗瑰埆澶с傜洰鍓嶇湅鏉ュ敮涓鐨勪綔鐢ㄦ槸PhysX鐗╃悊鍔犻燂紝浣嗘槸浣跨敤瀹冪殑娓告垙涓嶆槸寰堝銆傛湰鏉UDA寰堟湁鍓嶉旂殑锛屼絾鏄殢鐫OpenCL鍜孌X11鐨勫彂甯冿紝CUDA鎰熻椹笂灏辫钀藉癁浜嗐侰UDA灏辨槸鍒╃敤鏄惧崱鏉ヨ緟鍔〤PU杩涜璁＄畻锛屽拰DirectX鐗堟湰娌℃湁鐩存帴鍏崇郴銆侼Vidia鐜板湪鐨勬柊鏄惧崱閮鏀寔DX10鐨勶紝Directx9.0c鑲畾鏀寔浜嗐
绛旓細CUDA8.0鏀寔鐨lib/涓湁寰堝父鐢ㄧ殑锛歝ublas锛堝熀纭绾挎т唬鏁拌绠楀簱锛孊asic Linear Algebra Subprograms锛,cufft锛堝揩閫熷倕閲屽彾鍙樻崲锛,curand锛堥殢鏈烘暟锛,cusparse锛堢█鐤忕煩闃碉級锛宑usolver锛堣В绾挎ф柟绋嬬粍锛夌瓑绛夈CUDA9.0鍦╟usolver锛宑ugraph搴撲腑鍔犲叆浜嗘柊绠楁硶锛涘姞閫熶簡cublas锛宑ufft涓殑绠楁硶锛涘紩鍏ヤ簡Cooperative Groups鏉...
绛旓細浣滀负椤剁骇鐨勬樉鍗,鍐呴儴鐨16鏉℃覆鏌撶绾裤佹惌閰256MB 256bit鐨凣DDR3鏈湴鍐呭瓨銆傝繖娆炬樉鍗″畬鏁鏀寔Shader Model 3.0鐨凞irectX 9.0c,鍐呯疆CineFX 3.0寮曟搸,64浣嶇汗鐞嗘贩鍚堣繃婊ゃ32bit璞＄礌鐫鑹叉覆鏌撶簿搴︿竴搴斾勘鍏,甯︽湁绗簩浠ltraShadow闃村奖娓叉煋浼樺寲鎶鏈,姝ゅ杩樻敮鎸丆olor-compression(鑹插僵鍘嬬缉)鍜孼-compression(Z鍘嬬缉)鍘嬬缉鎶鏈侼VIDIA...
绛旓細妤间笂鏄湪鍐呮兜鍚?GT325M鐨勫疄闄呮父鎴忔ц兘鍜孏T130M宸笉澶,姣擥eForce7900GT/GTX瑕佷綆鐨.鑷充簬浠涔鏀寔DX9宸茬粡鐜╀笉浜嗘父鎴,灏辨槸涓娲捐儭瑷鑰屽凡,鐜板湪甯傞潰涓80%鐨勬父鎴忎粛鐒跺熀浜嶥X9.0c鍒朵綔,鍓╀笅閭20%鐨凞X11/10.1娓告垙涔熻兘鍏煎DX9.0c鐗规晥.
绛旓細1,Shader 4.1 technology 40 nm Features DirectX Compute Support (Windows 7),CUDA,OpenCL,HybridPower,PhysX Notebook Size medium sized Date of Announcement 10.01.2010 Information 142 Gigaflops 銆愯ˉ鍏呫慓eForce 320M锛汫eForce 315M锛汫eForce 310M锛汫eForce 305M杩欏嚑涓鏄惧崱閮鏀寔DirectX 10.1,...
