- Joined
- Oct 9, 2007
- Messages
- 46,390 (7.68/day)
- Location
- Hyderabad, India
| System Name | RBMK-1000 |
|---|---|
| Processor | AMD Ryzen 7 5700G |
| Motherboard | ASUS ROG Strix B450-E Gaming |
| Cooling | DeepCool Gammax L240 V2 |
| Memory | 2x 8GB G.Skill Sniper X |
| Video Card(s) | Palit GeForce RTX 2080 SUPER GameRock |
| Storage | Western Digital Black NVMe 512GB |
| Display(s) | BenQ 1440p 60 Hz 27-inch |
| Case | Corsair Carbide 100R |
| Audio Device(s) | ASUS SupremeFX S1220A |
| Power Supply | Cooler Master MWE Gold 650W |
| Mouse | ASUS ROG Strix Impact |
| Keyboard | Gamdias Hermes E2 |
| Software | Windows 11 Pro |
NVIDIA's Turing architecture is one of the biggest leaps in computer graphics in 20 years. Here's a look at the latest developer software releases to take advantage of this cutting-edge GPU. CUDA 10: CUDA 10 includes support for Turing GPUs, performance optimized libraries, a new asynchronous task-graph programming model, enhanced CUDA & graphics API interoperability, and new developer tools. CUDA 10 also provides all the components needed to build applications for NVIDIA's most powerful server platforms for AI and high performance computing (HPC) workloads, both on-prem (DGX-2) and in the cloud (HGX-2).
TensorRT 5 - Release Candidate: TensorRT 5 delivers up to 40x faster inference performance over CPUs through new optimizations, APIs and support for Turing GPUs. It optimizes mixed precision inference dramatically across apps such as recommenders, neural machine translation, speech and natural language processing. TensorRT 5 highlights include INT8 APIs offering new flexible workflows, optimization for depthwise separable convolution, support for Xavier-based NVIDIA Drive platforms and the NVIDIA DLA accelerator. In addition, TensorRT 5 brings support for Windows and CentOS Operating Systems.
cuDNN 7.3: Deep learning frameworks using cuDNN 7.3 can leverage new features and performance of the Turing architectures to deliver faster training performance. cuDNN 7.3 highlights include, improved grouped convolution for NHWC data format, and dilated convolution performance for popular models such as ResNet50, DeepSpeech2 and Wavenet.
NCCL 2.3: Deep learning frameworks using NCCL 2.3 and later can leverage new features and performance of the Volta and Turing architecture to deliver high-performance and efficient multi-node, multi-GPU scaling of deep learning training. New features include improved low latency algorithms for small message sizes and finer control of when to use GPU Direct P2P and RDMA.
CUTLASS 1.1: CUTLASS 1.1 allows developers to use Turing Tensor Cores for high performance matrix multiplication in CUDA C++. New features include support for CUDA 10 and new warp matrix functions to access the sub-byte capabilities of Turing to enable deep learning research with ultra low-precision.
NVIDIA RTX
NGX SDK: NGX is a new deep learning-based technology stack bringing AI-based features that accelerate and enhance graphics, photos imaging and video processing directly into applications. The NGX SDK provides pre-trained networks, making it easy for developers to integrate AI features. The SDK will be available in the next few weeks.
VRWorks Graphics 3.0: VRWorks Graphics features are aimed at Game and Application developers and bring a new level of visual fidelity, performance, and responsiveness to virtual reality. This version paired with Turing based GPUs brings many new technologies including Variable Rate Shading and Multi-View Rendering. Variable Rate Shading is a new rendering technique that increases rendering performance by applying full GPU shading horsepower to detailed areas of the scene, and less GPU horsepower to less detailed areas. Multi-View Rendering expands on Single Pass Stereo's features, increasing the number of projection centers or views for a single rendering pass from two to four. All four of the views available in a single pass are now position-independent and can shift along any axis in the projective space allowing support for new display configurations and canted displays for extremely wide fields of view.
Developer Tools
Nsight Compute 1.0: NVIDIA Nsight Compute is a next-gen tool that provides interactive CUDA API debugging and kernel profiling. This version of Nsight Compute offers fast data collection of detailed performance metrics and API debugging via a user interface and command line tool.
Nsight Systems 2018.2: NVIDIA Nsight Systems is a low overhead performance analysis tool designed to provide the insights developers need to optimize their software, like identifying bottlenecks across the CPUs and GPUs. Updates in Nsight Systems 2018.2 include CUDA 10 support, command line interface improvements to cover new usage scenarios, and various compatibility and usability enhancements.
Nsight Graphics 2018.5: Nsight Graphics is a standalone developer tool that enables you to debug, profile, and export frames built with popular graphics APIs. Version 2018.5 makes GPU Trace publicly available, adds support for Direct3D 12 DXR and Vulkan Ray Tracing extensions, extends the pixel history feature to cover DirectX 12, and completes support for the Windows RS3 DirectX 12 SDK.
Nsight VSE 6.0: NVIDIA Nsight Visual Studio Edition is an application development environment for GPUs that allows you to build, debug, profile, and trace a wide range of applications. Updates in Nsight VSE 6.0 include graphics debugging with ray tracing support and enhanced compute debugging and analysis with CUDA 10 support.
View at TechPowerUp Main Site
TensorRT 5 - Release Candidate: TensorRT 5 delivers up to 40x faster inference performance over CPUs through new optimizations, APIs and support for Turing GPUs. It optimizes mixed precision inference dramatically across apps such as recommenders, neural machine translation, speech and natural language processing. TensorRT 5 highlights include INT8 APIs offering new flexible workflows, optimization for depthwise separable convolution, support for Xavier-based NVIDIA Drive platforms and the NVIDIA DLA accelerator. In addition, TensorRT 5 brings support for Windows and CentOS Operating Systems.
cuDNN 7.3: Deep learning frameworks using cuDNN 7.3 can leverage new features and performance of the Turing architectures to deliver faster training performance. cuDNN 7.3 highlights include, improved grouped convolution for NHWC data format, and dilated convolution performance for popular models such as ResNet50, DeepSpeech2 and Wavenet.
NCCL 2.3: Deep learning frameworks using NCCL 2.3 and later can leverage new features and performance of the Volta and Turing architecture to deliver high-performance and efficient multi-node, multi-GPU scaling of deep learning training. New features include improved low latency algorithms for small message sizes and finer control of when to use GPU Direct P2P and RDMA.
CUTLASS 1.1: CUTLASS 1.1 allows developers to use Turing Tensor Cores for high performance matrix multiplication in CUDA C++. New features include support for CUDA 10 and new warp matrix functions to access the sub-byte capabilities of Turing to enable deep learning research with ultra low-precision.
NVIDIA RTX
NGX SDK: NGX is a new deep learning-based technology stack bringing AI-based features that accelerate and enhance graphics, photos imaging and video processing directly into applications. The NGX SDK provides pre-trained networks, making it easy for developers to integrate AI features. The SDK will be available in the next few weeks.
VRWorks Graphics 3.0: VRWorks Graphics features are aimed at Game and Application developers and bring a new level of visual fidelity, performance, and responsiveness to virtual reality. This version paired with Turing based GPUs brings many new technologies including Variable Rate Shading and Multi-View Rendering. Variable Rate Shading is a new rendering technique that increases rendering performance by applying full GPU shading horsepower to detailed areas of the scene, and less GPU horsepower to less detailed areas. Multi-View Rendering expands on Single Pass Stereo's features, increasing the number of projection centers or views for a single rendering pass from two to four. All four of the views available in a single pass are now position-independent and can shift along any axis in the projective space allowing support for new display configurations and canted displays for extremely wide fields of view.
Developer Tools
Nsight Compute 1.0: NVIDIA Nsight Compute is a next-gen tool that provides interactive CUDA API debugging and kernel profiling. This version of Nsight Compute offers fast data collection of detailed performance metrics and API debugging via a user interface and command line tool.
Nsight Systems 2018.2: NVIDIA Nsight Systems is a low overhead performance analysis tool designed to provide the insights developers need to optimize their software, like identifying bottlenecks across the CPUs and GPUs. Updates in Nsight Systems 2018.2 include CUDA 10 support, command line interface improvements to cover new usage scenarios, and various compatibility and usability enhancements.
Nsight Graphics 2018.5: Nsight Graphics is a standalone developer tool that enables you to debug, profile, and export frames built with popular graphics APIs. Version 2018.5 makes GPU Trace publicly available, adds support for Direct3D 12 DXR and Vulkan Ray Tracing extensions, extends the pixel history feature to cover DirectX 12, and completes support for the Windows RS3 DirectX 12 SDK.
Nsight VSE 6.0: NVIDIA Nsight Visual Studio Edition is an application development environment for GPUs that allows you to build, debug, profile, and trace a wide range of applications. Updates in Nsight VSE 6.0 include graphics debugging with ray tracing support and enhanced compute debugging and analysis with CUDA 10 support.
View at TechPowerUp Main Site
: "tensor processing unit 
