S8901 Quadro for AI, VR and Simulation Carl Flygare, PNY Allen - PowerPoint PPT Presentation

S8901 – Quadro for AI, VR and Simulation

Carl Flygare, PNY Allen Bourgoyne, NVIDIA Quadro Product Marketing Manager Senior Product Marketing Manager

“The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.” Edsger Dijkstra

Intelligence Abounds in Nature A very small sampling

Technological Intelligence Homo sapiens’ essential differentiator Thalmocortical brain network 3 million neurons, 476 million synapses Full human brain 106 billion neurons, 1,000 trillion synapses

Artificial Intelligence: Where we Stand Today Google’s IQ is slightly below a six-year-old human’s Google 47.28 | 78.42% increase since 2014 Baidu 32.92 | 40.08% increase since 2014 Microsoft Bing 31.98 Apple Siri 23.90 AI IQ’s significantly lower than an 18-year-old’s average 97 score In 2014 two of the three researchers found Google had an IQ of 26.5 compared to Baidu’s 23.5 Source: http://www.zdnet.com/article/google-ai-vs-siri-vs-bing-iq-tests-show-one-is-smartest-by-a-mile/

NVIDIA Quadro Every segment benefits from AI, VR and simulation Manufacturing CAE Media and Entertainment Automotive AEC Energy (Oil and Gas) Scientific and Technical Healthcare

NVIDIA Quadro | AI, VR and Simulation Open New Possibilities AI (Deep Learning) Development, Collaborative VR, CAE Simulations, GP100 16 GB GV100 32 GB Ultimate CAD Models, Photorealistic Rendering and GPGPU Compute Collaborative VR, Extremely Complex CAD Models, CAE, Photorealistic P6000 24 GB Rendering, DCC and VFX, Seismic Exploration, 3D Medical Imaging Professional VR, Very Complex CAD Models, CAE, Photorealistic P5000 16 GB Rendering, Advanced DCC and VFX, 3D Medical Imaging Professional VR, Complex CAD Models, CAE, Photorealistic P4000 8 GB Rendering, Complex DCC and VFX, Medical Imaging Medium Size and Complexity CAD Models, P2000 5 GB PLM, Basic DCC, Medical Imaging P1000 4 GB Small and Simple CAD P620 2 GB Models, Entry PLM P400 2 GB Entry Basic Mid Range Upper Range High End Ultra High End

NVIDIA Quadro | AI, VR and Simulation Open New Possibilities AI (Deep Learning) Development, Collaborative VR, CAE Simulations, GP100 16 GB GV100 32 GB Ultimate CAD Models, Photorealistic Rendering and GPGPU Compute Collaborative VR, Extremely Complex CAD Models, CAE, Photorealistic P6000 24 GB Rendering, DCC and VFX, Seismic Exploration, 3D Medical Imaging Professional VR, Very Complex CAD Models, CAE, Photorealistic P5000 16 GB Rendering, Advanced DCC and VFX, 3D Medical Imaging Professional VR, Complex CAD Models, CAE, Photorealistic P4000 8 GB Rendering, Complex DCC and VFX, Medical Imaging Medium Size and Complexity CAD Models, P2000 5 GB PLM, Basic DCC, Medical Imaging P1000 4 GB Small and Simple CAD P620 2 GB Models, Entry PLM P400 2 GB Entry Basic Mid Range Upper Range High End Ultra High End

NVIDIA Quadro GP100 NVIDIA Quadro GV100 | Reinventing the Workstation for AI

NVIDIA Quadro GP100 NVIDIA Quadro GV100 x 2 | NVLink Scalable Workstation AI

NVIDIA Quadro GV100 and NVLink Scaling performance and memory * High speed GPU and memory connection for GV100 ▪ NVLink combines two GV100s for twice the compute power and 64 GB of memory ▪ Up to 200 GB/sec bidirectional bandwidth, 25% improvement ▪ Used in pairs, two dedicated NVLink connectors on GV100 boards ▪ Provides SLI functionality for GV100 boards * Application support for NVLink required. Maximum of two GV100 boards can be connected with NVLink.

NVIDIA Quadro GV100 Technical specifications GPU Architecture Volta CUDA and Tensor Cores 2560 (FP64), 5120 (FP32), 640 (Tensor) Memory Capacity 32 GB HBM2 Peak Memory Bandwidth 870 GB/sec FP64 (Double Precision) 7.4 TFLOPS | 42% improvement FP32 (Single Precision) 14.8 TFLOPS | 44% improvement FP16 (Half Precision) 118.5 TFLOPS (Matrix Multiply with FP16 or 32 Accumulate) INT8 (Integer) 59.3 TOPS | 26% improvement System Interface PCI Express Gen 3 x16 NVLink 200 GB/sec Bidirectional | 25% improvement Display Connectors 4x DisplayPort 1.4 with HDCP 2.2 4K Display Support 4x 4096 x 2160 at 120 Hz with HDR 5K Display Support 4x 5120 x 2880 at 60 Hz with HDR 8K Display Support 2x 7680 x 4320 at 60 Hz with HDR VR Ready and Stereo Yes, Stereo via 3-pin mini-DIN Connector Bracket

NVIDIA Quadro GV100 Unmatched compute capabilities FP 64 TFLOPS 7.4 FP 32 TFLOPS 14.8 FP 16 TFLOPS 118.5 INT 8 TOPS 59.3

NVIDIA Quadro GV100 Features and benefits relative to GP100 GP100 GV100 Benefit GPU Architecture Pascal Volta Most powerful, efficient and AI optimized GPU CUDA Cores 3584 5120 Significantly greater compute and rendering performance FP64 Performance 5.2 TFLOPS 7.2 TFLOPS 1.4x greater FP64 compute performance Memory Size 16 GB HBM2 32 GB HBM2 2.0x memory capacity Memory Bus Width 4096-bit 4096-bit Radically advanced memory bus implementation Peak Memory Bandwidth 717 GB/sec 870 GB/sec Move data to and from GPU 1.2x faster Display Support 4x DP 1.4 + 1x DVI-D DL 4x DP 1.4 and HDCP 2.2 Supports four 4K, 5K or 8K displays, latest HDCP HDR Image Support Yes Yes More lifelike images Advanced Display Quadro Sync II Quadro Sync II Synchronize up to 8 GPUs per system VR Ready Yes Yes, GV100 implements full suite of hardware optimizations NVLink NVLink (First Generation) NVLink (Second Generation) Higher performance means lower latency Board Power 235 W 250 W Better performance per Watt Auxiliary Power Connector 8-pin PCIe 8-pin PCIe Simplified power supply connectivity Form Factor 4.4” H x 10.5” L Dual Slot 4.4” H x 10.5” L Dual Slot No significant mechanical or thermal changes

NVIDIA Quadro GV100 Redefines state of the art across essential solutions Artificial Intelligence RTX Rendering Compute Immersive Visualization (VR) Tensor processor cores Unrivaled FP32 performance Industry leading HPC capabilities Includes VR hardware optimizations NVIDIA GPU deep learning stack Largest models in GPU memory Work with largest datasets Full NVIDIA VRWORKS support ISV DL and ML framework optimization AI accelerated photorealistic rendering Integrate simulation into design process Create new AI-augmented technologies Iterate and innovate faster Neural network character animation Utilize generative design algorithms Visualize the largest datasets Reduce training time Apply AI to simultaneous video streams Fastest FEA, CFD, CEM available Collaborative VR environments (Holodeck) Connect two GV100 boards with NVLink to provide 64 GB of memory and twice the GPU processing power in standard workstation enclosures

NVIDIA Quadro GV100 RTX rendering lets you dream and create at the speed of thought Architectural Design Product Design Media and Entertainment Visualize cities or urban street scenes in Design with physically based lights and Perfect every shot with GPI accelerated every photorealistic detail materials in realtime and AI enhanced rendering Work at full fidelity, utilizing massive datasets with 2x larger memory capacity Master rendering projects interactively with AI (Deep Neural Network) technology

NVIDIA Quadro RTX supercharges rendering with AI accelerated denoising Denoising On Denoising Off Denoising Off 20 Frames 20 Frames 290 Frames High quality results with fluid visual interactivity throughout the design process

NVIDIA Quadro Companies working with NVIDIA’s OptiX AI denoiser technology Image courtesy of Isotropix, rendered with Clarisse and denoised with NVIDIA OptiX.

NVIDIA Quadro CAD and CAE workflow elements Post-Processing Design (CAD) Pre-Processing Simulation (CAE)

NVIDIA Quadro GV100 Benefit from the ultimate immersive experiences RTX Rendered Graphics Interactive Physics Realtime Collaboration GPU-Accelerated AI 2x larger memory capacity lets you work with high fidelity, massive datasets (v. GP100) Benefit from unconstrained Holodeck experiences with full-featured VR performance and capabilities

NVIDIA Quadro GV100 Realize new opportunities with AI Development Aggregation Inferencing At-The-Edge NGC Retail store inferencing with Quadro by DeepBlue Technology, China 32 GB or 64 GB capacity (NVLink) trains neural networks with massive datasets Develop with NVIDIA optimized Deep Learning frameworks and deploy with NGC interoperability and scalability Accelerate AI training and inferencing on workstations with Tensor cores and NVLink

NVIDIA Quadro GV100 AI Training Performance Up to 2x improvement in Deep Learning training performance* 800 700 Caffe ResNet-50 Training IPS Tensor Flow ResNet-50 Training IPS 700 600 600 500 500 400 400 300 300 200 200 100 100 GP100 Batch Size 128 GP100 Batch Size 256 GV100 Batch Size 512 GV100 Batch Size 128 GV 100 Batch Size 256 GV100 Batch Size 256 * Based on TensorFlow Resnet-50 Training. Tests run on dual Intel Xeon E5 2690 v4 at 2.6 GHz, NVIDIA driver version 390.19, ResNet-50 Training.

NVIDIA Quadro GV100 Deep Learning Training Performance Over 2x improvement in Deep Learning training and inference performance* 700 700 Tensor FlowResNet-50 Training TensorRT ResNet-50 Inference 600 600 500 500 400 400 300 300 200 200 100 100 GP100 Batch Size 256 1 2 4 8 GV100 Batch Size 256 GV 100 Batch Size 512 Batch Size * Based on TensorFlow Resnet-50 Training, TensorRT ResNet-50 Inference tests. Tests run on dual Intel Xeon E5 2690 v4 at 2.6 GHz, NVIDIA driver version 390.19, ResNet-50 Training.