Ampere is the codename for a graphics processing unit (GPU) microarchitecture developed by Nvidia as the successor to both the Volta and Turing architectures, officially announced on May 14, 2020. It is named after French mathematician and physicist André-Marie Ampère.[1][2] Nvidia announced the next-generation GeForce 30 series consumer GPUs at a GeForce Special Event on September 1, 2020.[3][4] Nvidia announced A100 80GB GPU at SC20 on November 16, 2020.[5] Mobile RTX graphics cards and the RTX 3060 were revealed on January 12, 2021.[6][further explanation needed] Nvidia also announced Ampere's successor, Hopper, at GTC 2022, and "Ampere Next Next" for a 2024 release at GPU Technology Conference 2021.
Custom version of Samsung's 8 nm process (8N) for the GeForce 30 series[8]
Third-generation Tensor Cores with FP16, bfloat16, TensorFloat-32 (TF32) and FP64 support and sparsity acceleration.[9] The individual Tensor cores have with 256 FP16 FMA operations per second 4x processing power (GA100 only, 2x on GA10x) compared to previous Tensor Core generations; the Tensor Core Count is reduced to one per SM.
Second-generation ray tracing cores; concurrent ray tracing, shading, and compute for the GeForce 30 series
Adds new hardware-based 5-core JPEG decode (NVJPG) with YUV420, YUV422, YUV444, YUV400, RGBA. Should not be confused with Nvidia NVJPEG (GPU-accelerated library for JPEG encoding/decoding)
Announced and released on May 14, 2020 was the Ampere-based A100 accelerator.[9] The A100 features 19.5 teraflops of FP32 performance, 6912 CUDA cores, 40GB of graphics memory, and 1.6TB/s of graphics memory bandwidth.[15] The A100 accelerator was initially available only in the 3rd generation of DGX server, including 8 A100s.[9] Also included in the DGX A100 is 15TB of PCIe gen 4 NVMe storage,[15] two 64-core AMD Rome 7742 CPUs, 1 TB of RAM, and Mellanox-powered HDR InfiniBand interconnect. The initial price for the DGX A100 was $199,000.[9]
Comparison of accelerators used in DGX:[16][17][18]
ampere, microarchitecture, ampere, codename, graphics, processing, unit, microarchitecture, developed, nvidia, successor, both, volta, turing, architectures, officially, announced, 2020, named, after, french, mathematician, physicist, andré, marie, ampère, nvi. Ampere is the codename for a graphics processing unit GPU microarchitecture developed by Nvidia as the successor to both the Volta and Turing architectures officially announced on May 14 2020 It is named after French mathematician and physicist Andre Marie Ampere 1 2 Nvidia announced the next generation GeForce 30 series consumer GPUs at a GeForce Special Event on September 1 2020 3 4 Nvidia announced A100 80GB GPU at SC20 on November 16 2020 5 Mobile RTX graphics cards and the RTX 3060 were revealed on January 12 2021 6 further explanation needed Nvidia also announced Ampere s successor Hopper at GTC 2022 and Ampere Next Next for a 2024 release at GPU Technology Conference 2021 Nvidia AmpereRelease dateMay 14 2020 2020 05 14 Fabrication processTSMC 7 nm Professional Samsung 8 nm Consumer HistoryPredecessorTuring consumer Volta professional SuccessorAda Lovelace consumer Hopper professional Support statusSupportedEngraving of Andre Marie Ampere Contents 1 Details 1 1 Chips 2 A100 accelerator and DGX A100 3 Products using Ampere 4 See also 5 References 6 External linksDetails EditArchitectural improvements of the Ampere architecture include the following CUDA Compute Capability 8 0 for A100 and 8 6 for the GeForce 30 series 7 TSMC s 7 nm FinFET process for A100 Custom version of Samsung s 8 nm process 8N for the GeForce 30 series 8 Third generation Tensor Cores with FP16 bfloat16 TensorFloat 32 TF32 and FP64 support and sparsity acceleration 9 The individual Tensor cores have with 256 FP16 FMA operations per second 4x processing power GA100 only 2x on GA10x compared to previous Tensor Core generations the Tensor Core Count is reduced to one per SM Second generation ray tracing cores concurrent ray tracing shading and compute for the GeForce 30 series High Bandwidth Memory 2 HBM2 on A100 40GB amp A100 80GB GDDR6X memory for GeForce RTX 3090 RTX 3080 Ti RTX 3080 RTX 3070 Ti Double FP32 cores per SM on GA10x GPUs NVLink 3 0 with a 50Gbit s per pair throughput 9 PCI Express 4 0 with SR IOV support SR IOV is reserved only for A100 Multi instance GPU MIG virtualization and GPU partitioning feature in A100 supporting up to seven instances PureVideo feature set K hardware video decoding with AV1 hardware decoding 10 for the GeForce 30 series and feature set J for A100 5 NVDEC for A100 Adds new hardware based 5 core JPEG decode NVJPG with YUV420 YUV422 YUV444 YUV400 RGBA Should not be confused with Nvidia NVJPEG GPU accelerated library for JPEG encoding decoding Chips Edit GA100 11 GA102 GA103 GA104 GA106 GA107Comparison of Compute Capability GP100 vs GV100 vs GA100 12 GPU features NVIDIA Tesla P100 NVIDIA Tesla V100 NVIDIA A100GPU codename GP100 GV100 GA100GPU architecture NVIDIA Pascal NVIDIA Volta NVIDIA AmpereCompute capability 6 0 7 0 8 0Threads warp 32 32 32Max warps SM 64 64 64Max threads SM 2048 2048 2048Max thread blocks SM 32 32 32Max 32 bit registers SM 65536 65536 65536Max registers block 65536 65536 65536Max registers thread 255 255 255Max thread block size 1024 1024 1024FP32 cores SM 64 64 64Ratio of SM registers to FP32 cores 1024 1024 1024Shared Memory Size SM 64 KB Configurable up to 96 KB Configurable up to 164 KBComparison of Precision Support Matrix 13 14 Supported CUDA Core Precisions Supported Tensor Core PrecisionsFP16 FP32 FP64 INT1 INT4 INT8 TF32 BF16 FP16 FP32 FP64 INT1 INT4 INT8 TF32 BF16NVIDIA Tesla P4 No Yes Yes No No Yes No No No No No No No No No NoNVIDIA P100 Yes Yes Yes No No No No No No No No No No No No NoNVIDIA Volta Yes Yes Yes No No Yes No No Yes No No No No No No NoNVIDIA Turing Yes Yes Yes No No Yes No No Yes No No Yes Yes Yes No NoNVIDIA A100 Yes Yes Yes No No Yes No Yes Yes No Yes Yes Yes Yes Yes YesLegend FPnn floating point with nn bits INTn integer with n bits INT1 binary TF32 TensorFloat32 BF16 bfloat16Comparison of Decode Performance Concurrent streams H 264 decode 1080p30 H 265 HEVC decode 1080p30 VP9 decode 1080p30 V100 16 22 22A100 75 157 108A100 accelerator and DGX A100 EditAnnounced and released on May 14 2020 was the Ampere based A100 accelerator 9 The A100 features 19 5 teraflops of FP32 performance 6912 CUDA cores 40GB of graphics memory and 1 6TB s of graphics memory bandwidth 15 The A100 accelerator was initially available only in the 3rd generation of DGX server including 8 A100s 9 Also included in the DGX A100 is 15TB of PCIe gen 4 NVMe storage 15 two 64 core AMD Rome 7742 CPUs 1 TB of RAM and Mellanox powered HDR InfiniBand interconnect The initial price for the DGX A100 was 199 000 9 Comparison of accelerators used in DGX 16 17 18 AcceleratorH100 A100 80GB A100 40GB V100 32GB V100 16GB P100Architecture Socket FP32CUDACores FP64 Cores excl Tensor MixedINT32 FP32Cores INT32Cores BoostClock MemoryClock MemoryBus Width MemoryBandwidth VRAM SinglePrecision FP32 DoublePrecision FP64 INT8 non Tensor INT8Dense Tensor INT32 FP16 FP16Dense Tensor bfloat16Dense Tensor TensorFloat 32 TF32 Dense Tensor FP64Dense Tensor Interconnect NVLink GPU L1 Cache Size L2 Cache Size TDP GPUDie Size TransistorCount Manufacturing ProcessHopper SXM5 16896 4608 16896 N A 1780 MHz 4 8Gbit s HBM3 5120 bit 3072GB sec 80GB 60 TFLOPs 30 TFLOPs N A 4000 TOPs N A N A 2000 TFLOPs 2000 TFLOPs 1000 TFLOPs 60 TFLOPs 900GB sec GH100 25344KB 192KBx132 51200 KB 700W 814 mm2 80B TSMC 4 nm N4Ampere SXM4 6912 3456 6912 N A 1410 MHz 3 2Gbit s HBM2 5120 bit 2039GB sec 80GB 19 5 TFLOPs 9 7 TFLOPs N A 624 TOPs 19 5 TOPs 78 TFLOPs 312 TFLOPs 312 TFLOPs 156 TFLOPs 19 5 TFLOPs 600GB sec GA100 20736KB 192KBx108 40960 KB 400W 826 mm2 54 2B TSMC 7 nm N7Ampere SXM4 6912 3456 6912 N A 1410 MHz 2 4Gbit s HBM2 5120 bit 1555GB sec 40GB 19 5 TFLOPs 9 7 TFLOPs N A 624 TOPs 19 5 TOPs 78 TFLOPs 312 TFLOPs 312 TFLOPs 156 TFLOPs 19 5 TFLOPs 600GB sec GA100 20736KB 192KBx108 40960 KB 400W 826 mm2 54 2B TSMC 7 nm N7Volta SXM3 5120 2560 N A 5120 1530 MHz 1 75Gbit s HBM2 4096 bit 900GB sec 32GB 15 7 TFLOPs 7 8 TFLOPs 62 TOPs N A 15 7 TOPs 31 4 TFLOPs 125 TFLOPs N A N A N A 300GB sec GV100 10240KB 128KBx80 6144 KB 350W 815 mm2 21 1B TSMC 12 nm FFNVolta SXM2 5120 2560 N A 5120 1530 MHz 1 75Gbit s HBM2 4096 bit 900GB sec 16GB 15 7 TFLOPs 7 8 TFLOPs 62 TOPs N A 15 7 TOPs 31 4 TFLOPs 125 TFLOPs N A N A N A 300GB sec GV100 10240KB 128KBx80 6144 KB 300W 815 mm2 21 1B TSMC 12 nm FFNPascal SXM N A 1792 3584 N A 1480 MHz 1 4Gbit s HBM2 4096 bit 720GB sec 16GB 10 6 TFLOPs 5 3 TFLOPs N A N A N A 21 2 TFLOPs N A N A N A N A 160GB sec GP100 1344KB 24KBx56 4096 KB 300W 610 mm2 15 3B TSMC 16 nm FinFET Products using Ampere EditGeForce MX series GeForce MX570 mobile GA107 GeForce 20 series GeForce RTX 2050 mobile GA107 GeForce 30 series GeForce RTX 3050 mobile GA107 GeForce RTX 3050 GA106 or GA107 19 GeForce RTX 3050 Ti mobile GA107 GeForce RTX 3060 mobile GA106 GeForce RTX 3060 GA106 or GA104 20 GeForce RTX 3060 Ti GA104 or GA103 21 GeForce RTX 3070 mobile GA104 GeForce RTX 3070 GA104 GeForce RTX 3070 Ti mobile GA104 GeForce RTX 3070 Ti GA104 GeForce RTX 3080 mobile GA104 GeForce RTX 3080 GA102 GeForce RTX 3080 12GB GA102 GeForce RTX 3080 Ti mobile GA103 GeForce RTX 3080 Ti GA102 GeForce RTX 3090 GA102 GeForce RTX 3090 Ti GA102 Nvidia Workstation GPUs formerly Quadro RTX A2000 mobile GA107 RTX A2000 GA106 RTX A3000 mobile GA104 RTX A4000 mobile GA104 RTX A4000 GA104 RTX A4500 GA102 RTX A5000 mobile GA104 RTX A5000 GA102 RTX A5500 GA102 RTX A6000 GA102 Nvidia Data Center GPUs formerly Tesla Nvidia A2 GA107 Nvidia A10 GA102 Nvidia A16 4 GA107 Nvidia A30 GA100 Nvidia A40 GA102 Nvidia A100 GA100 Nvidia A100 80GB GA100 Products using Ampere per Chip GA107 GA106 GA104 GA103 GA102 GA100GeForce MX series GeForce MX570 mobile GeForce 20 series GeForce RTX 2050 mobile GeForce 30 series GeForce RTX 3050 mobile GeForce RTX 3050 19 GeForce RTX 3050 Ti mobile GeForce RTX 3050GeForce RTX 3060 mobile GeForce RTX 3060 GeForce RTX 3060 20 GeForce RTX 3060 TiGeForce RTX 3070 mobile GeForce RTX 3070GeForce RTX 3070 Ti mobile GeForce RTX 3070 TiGeForce RTX 3080 mobile GeForce RTX 3060 Ti 21 GeForce RTX 3080 Ti mobile GeForce RTX 3080GeForce RTX 3080 TiGeForce RTX 3090GeForce RTX 3090 Ti Nvidia Workstation GPUs RTX A2000 mobile RTX A2000 RTX A3000 mobile RTX A4000 mobile RTX A4000RTX A5000 mobile RTX A4500RTX A5000RTX A5500RTX A6000 Nvidia Data Center GPUs Nvidia A2Nvidia A16 Nvidia A10Nvidia A40 Nvidia A30Nvidia A100See also EditList of Nvidia graphics processing units Nvidia NVENC Nvidia NVDECReferences Edit Newsroom NVIDIA NVIDIA s New Ampere Data Center GPU in Full Production NVIDIA Newsroom Newsroom NVIDIA Ampere Architecture In Depth NVIDIA Developer Blog May 14 2020 Newsroom NVIDIA NVIDIA Delivers Greatest Ever Generational Leap with GeForce RTX 30 Series GPUs NVIDIA Newsroom Newsroom NVIDIA GeForce Ultimate Countdown NVIDIA NVIDIA Doubles Down Announces A100 80GB GPU Supercharging World s Most Powerful GPU for AI Supercomputing Join us for an NVIDIA GeForce RTX Game on Special Broadcast Event I 7 Compute Capability 8 x docs nvidia com Retrieved September 23 2020 B Dominik Samsung s old 8nm tech at the heart of NVIDIA s monstrous Ampere cards SamMobile Retrieved September 19 2020 a b c d e Smith Ryan May 14 2020 NVIDIA Ampere Unleashed NVIDIA Announces New GPU Architecture A100 GPU and Accelerator AnandTech GeForce RTX 30 Series GPUs Ushering In A New Era of Video Content With AV1 Decode NVIDIA Morgan Timothy Prickett May 29 2020 Diving Deep Into The Nvidia Ampere GPU Architecture The Next Platform Retrieved March 24 2022 NVIDIA A100 Tensor Core GPU Architecture PDF www nvidia com Retrieved September 18 2020 NVIDIA Tensor Cores Versatility for HPC amp AI NVIDIA Abstract docs nvidia com a b Tom Warren James Vincent May 14 2020 Nvidia s first Ampere GPU is designed for data centers and AI not your PC The Verge Smith Ryan March 22 2022 NVIDIA Hopper GPU Architecture and H100 Accelerator Announced Working Smarter and Harder AnandTech Smith Ryan May 14 2020 NVIDIA Ampere Unleashed NVIDIA Announces New GPU Architecture A100 GPU and Accelerator AnandTech NVIDIA Tesla V100 tested near unbelievable GPU power TweakTown September 17 2017 a b Igor Wallossek February 13 2022 The two faces of the GeForce RTX 3050 8GB Igor s Lab Retrieved February 23 2022 a b Shilov Anton September 25 2021 Gainward and Galax List GeForce RTX 3060 Cards With GA104 GPU Tom s Hardware Retrieved September 23 2022 a b Tyson Mark February 23 2022 Zotac Debuts First RTX 3060 Ti Desktop Cards With GA103 GPU Tom s Hardware Retrieved September 23 2022 External links EditNVIDIA A100 Tensor Core GPU Architecture whitepaper Nvidia Ampere GA102 GPU Architecture whitepaper Nvidia Ampere Architecture Nvidia A100 Tensor Core GPU NVIDIA Ampere Architecture In Depth Retrieved from https en wikipedia org w index php title Ampere microarchitecture amp oldid 1129192550, wikipedia, wiki, book, books, library,
