SLIDE 1
ABHIJIT PATAIT
- SR. MANAGER, NVIDIA
AGENDA
GPU Video Encoding Overview NVIDIA Video Encoding Capabilities
Kepler, Maxwell Gen 1, Maxwell Gen 2
HIGH-PERFORMANCE GPU VIDEO ENCODING ABHIJIT PATAIT SR. MANAGER, - - PowerPoint PPT Presentation
HIGH-PERFORMANCE GPU VIDEO ENCODING ABHIJIT PATAIT SR. MANAGER, - - PowerPoint PPT Presentation
HIGH-PERFORMANCE GPU VIDEO ENCODING ABHIJIT PATAIT SR. MANAGER, NVIDIA AGENDA GPU Video Encoding Overview NVIDIA Video Encoding Capabilities Kepler, Maxwell Gen 1, Maxwell Gen 2 Software API Performance & Quality Roadmap WHY GPU VIDEO
SLIDE 2
SLIDE 3
WHY GPU VIDEO ENCODING?
SLIDE 4
BENEFITS
Low power
Fixed function hardware, free CPU Reduced memory transfers
Low latency High performance Higher density Scalability
Automatic benefit from improvements in hardware
Ease of programming
Linux, Windows, C/C++, Application portability
SLIDE 5
NVIDIA VIDEO ENCODER CAPABILITIES
SLIDE 6
MAIN FEATURES
Feature Benefits H.264 base, main, high profiles Wide range of use-cases H.265/HEVC main profile Lower bitrates at same quality High performance (4K @ 60 fps) “Blazing-speed” encoding YUV 4:2:0 and 4:4:4 support High quality encoding without chroma subsampling QP maps Customizable quality, region of interest encoding 4K encoding in hardware High resolution encode API - NV Encode SDK & GRID SDK Flexible, Win/Linux, DirectX/CUDA Independent of CUDA Use CUDA and encode simultaneously
SLIDE 7
FEATURE COMPARISON
Kepler Maxwell Gen 1 (GM10x) Maxwell Gen 2 (GM20x) H.264 only H.264 only H.264 and HEVC/H.265 Planar 4:4:4 & proprietary 4:4:4; no lossless encoding Standard 4:4:4 and H.264 lossless encoding Standard 4:4:4 and H.264 lossless encoding ~240 fps 2-pass encoding @ 720p ~500 fps 2-pass encoding @ 720p ~900 fps 2-pass encoding @ 720p GRID K340/K520, K1/K2, Quadro, Tesla K10/K20 Maxwell-based GRID & Quadro products TBA GeForce – 2 full-speed encode sessions/system GeForce – 2 full-speed encode sessions/system GeForce – 2 full-speed encode sessions/system NV Encode SDK 1.0-5.0 (Now) NV Encode SDK 4.0+ (Now) NV Encode SDK 5.0+ (Now) GRID SDK 1.x, 2.2, 2.3 (Now) GRID SDK 3.0+ (Now) In development
SLIDE 8
WHAT’S NEW – HARDWARE
HEVC
8-bit encoding Main8 profile Optimized for low-latency applications (I and P frames) > 300 fps at very high quality 720p
H.264
Improved performance (~80% higher compared to 1st Gen Maxwell) 4:4:4 and lossless
SLIDE 9
WHAT’S NEW - SOFTWARE
NVENC SDK 5.0 NVIDIA GPU driver 347.18 and above HEVC
Unified API for H.264 and HEVC Linux & Windows Intra refresh, ref-pic invalidation, etc. for H.264 and HEVC
Support for all NVENC hardware up to GM20x Adaptive quantization Quality improvements All-new sample applications, including a performance application
SLIDE 10
SOFTWARE API
SLIDE 11
USING NVENC NVENC SDK
- No capture
- Transcoding
- Archiving
- Video editing
- CUDA pre-process +
encoding
- Granular encoder settings
- D3D, CUDA interop
Direct Encode
GRID SDK
- Capture + encode
- Optimized for low-latency
apps
- Capture + CUDA pre-
process + encoding
- Encoder settings
- ptimized for streaming
- D3D, CUDA interop
Capture + Encode
SLIDE 12
DIRECT ENCODE (NVENC SDK)
Client application NVENC API NVENC Driver DirectX Driver CUDA Driver NVENC firmware + hardware Initialize, Configure HW HW Encode Encoded bitstream Configure, Encode
SLIDE 13
CAPTURE & ENCODE (GRID SDK)
Client application NvFBC/NvIFR NVENC Driver DirectX/OGL Driver NVENC Hardware Capture YUV GPU 3D Engine DX/OGL Present Encode Encoded Bitstream
SLIDE 14
NVENC SDK (1/2)
Available on NVIDIA developer zone
https://developer.nvidia.com/nvidia-video-codec-sdk Current release: 5.0
Interface header, documentation, sample application .dll/.so included in the driver Unified API for Windows and Linux Works on x86/x64 API’s, presets, rate control modes for
Low-latency streaming Transcoding Video conferencing
SLIDE 15
NVENC SDK (2/2)
Unified API for H.264 and HEVC Flexibility
Dynamic resolution/bitrate change Low-level encoder settings Windows, Linux, DirectX, CUDA, OGL (via CUDA) Works on GeForce (2 sessions/system)
Error concealment
Reference picture invalidation Intra-refresh
Greater flexibility for quality/performance trade-off Lossless encoding only in NVENC SDK
SLIDE 16
GRID SDK ENCODE
NDA only – older release available on NV developer zone
https://developer.nvidia.com/grid-app-game-streaming
Current release: 3.1 (Now – NDA), 2.3 (Public) Interface header, documentation, sample apps .dll/.so included in the driver Windows and Linux Works on x86/x64 Presets and API’s for
Remote graphics (Cloud gaming, remote desktop, capture & stream) Optimized for low latency
SLIDE 17
QUALITY
SLIDE 18
H.264 QUALITY – 1-PASS ENCODING
34 36 38 40 42 44 46 6 8 10 12 15 18 20 PSNR (dB) bitrate (Mbps)
H.264 quality with 1-pass rate control
Default LL-Default HP HQ BD LL-HQ
SLIDE 19
H.264 QUALITY – 2-PASS ENCODING
34 36 38 40 42 44 46 6 8 10 12 15 18 20 PSNR (dB) bitrate (Mbps)
H.264 quality with 2-pass rate control
Default LL-Default HP HQ BD LL-HQ
SLIDE 20
COMPARISON: 1-PASS VS 2-PASS
37.5 38 38.5 39 39.5 40 40.5 Default LL-Default HP HQ BD LL-HQ PSNR (dB) Encoder preset
H.264 quality comparison: 1-pass vs 2-pass
1-pass 2-pass 1-pass 1-pass 1-pass 1-pass 1-pass 2-pass 2-pass 2-pass 2-pass 2-pass
SLIDE 21
BITRATE SAVINGS
39.5 dB 41.0 dB 42.0 dB 6 8 9.8 4 6 8
Bitrate savings - Default preset
39.5 dB 41.0 dB 42.0 dB 5.8 7.8 9.7 3.9 5.8 7.9
Bitrate savings - HQ preset 33% 25% 18%
33% 26% 19%
Bitrate savings H.264 H.264 H.264 H.264 H.264 H.264 HEVC HEVC HEVC HEVC HEVC HEVC
SLIDE 22
H.264 VS HEVC
Courtesy: Vanguard video
SLIDE 23
H.264 VS HEVC
Courtesy: Vanguard video
SLIDE 24
PERFORMANCE
SLIDE 25
H.264 PERFORMANCE – GM20X
1080p, GM20x
1 pass 2 pass 2 pass 2 pass 2 pass 1 pass 1 pass 1 pass
fps 50 fps 100 fps 150 fps 200 fps 250 fps 300 fps 350 fps 400 fps 450 fps 500 fps HP LL-HP HQ LL-HQ Single pass 464 fps 342 fps 291 fps 293 fps Two pass 306 fps 246 fps 171 fps 181 fps Encode FPS
H.264 Performance (1080p)
1 pass 1 pass 1 pass 1 pass 2 pass 2 pass 2 pass 2 pass
SLIDE 26
H.264/HEVC PERF COMPARISON
fps 50 fps 100 fps 150 fps 200 fps 250 fps 300 fps 350 fps HP LL-HP HQ LL-HQ H.264 306 fps 246 fps 171 fps 181 fps H.265 220 fps 214 fps 102 fps 153 fps Encode FPS
H.264/HEVC Performance: 2-pass
H.264 H.264 H.264 H.264 HEVC HEVC HEVC HEVC
SLIDE 27
PERFORMANCE - TREND
fps 200 fps 400 fps 600 fps 800 fps 1000 fps 1200 fps 1400 fps 1600 fps 1800 fps Kepler (2011) Maxwell Gen 1 (2013) Maxwell Gen 2 (2014) Future
Performance
SLIDE 28
ROADMAP
SLIDE 29
ROADMAP
Core GPU chip IP Motion estimation only mode – 2H2015 SAO, 10/12-bit, HEVC B-frames Lossless/4:4:4 Improved quality for screen content encoding ME performance and quality enhancements Today: 4K@60fps Next: 8K@??
SLIDE 30