Visual computing tasks such as computational imaging, image/video understanding, and real-time 3D graphics are key responsibilities of modern computer systems ranging from sensor-rich smart phones, autonomous robots, and large datacenters. These workloads demand exceptional system efficiency and this course examines the key ideas, techniques, and challenges associated with the design of parallel, heterogeneous systems that accelerate visual computing applications. This course is intended for systems students interested in architecting efficient graphics, image processing, and computer vision platforms (both new hardware architectures and domain-optimized programming frameworks for these platforms) and for graphics, vision, and machine learning students that wish to understand throughput computing principles to design new algorithms that map efficiently to these machines.
| Mar 29 |
|
|
Review of multi-core, multi-threading, SIMD, caches, and the value of hardware specialization
|
| Mar 31 |
|
|
Algorithms for taking raw sensor pixels to an RGB image: demosaicing, sharpening, correcting lens aberrations, multi-shot alignment/merging, image filtering
|
| Apr 05 |
|
|
Multi-scale processing with Gaussian and Laplacian pyramids, HDR (local tone mapping), portrait mode
|
| Apr 07 |
|
|
Autofocus, autoexposure, use of ML in advanced camera operations, the Frankencamera.
|
| Apr 12 |
|
|
Balancing locality, parallelism, and work, fusion and tiling, design of the Halide domain-specific language, automatically scheduling image processing pipelines
|
| Apr 14 |
|
|
Popular DNN trunks and topologies, where the compute lies in modern networks, data layout optimizations, scheduling decisions, modern code generation frameworks
|
| Apr 19 |
|
|
GPUs, TPUs, special instructions for DNN evaluation (and their efficiency vs custom ASIC), choice of precision in arithmetic, modern commercial DNN accelerators, flexibility vs efficiency trade-offs
|
| Apr 21 |
|
|
If the most important step of ML is acquiring labeled data for training and validation, why don't we have better systems for it?
|
| Apr 26 |
|
|
Systems for specifying models at a higher level of abstraction than DNN architecture graphs (Overton, Ludwig). Goal: removing the need for a low-level ML engineer.
|
| Apr 28 |
|
|
H.264 video representation/encoding, parallel encoding, motivations for ASIC acceleration, ML-based compression methods, emerging opportunities for compression when machines, not humans, will observe most images
|
| May 03 |
|
|
System design issues for building a video conferencing system: reducing latency, bandwidth, etc. How real-time video analysis will enable richer video-based applications.
|
| May 05 |
|
|
The light field, initial discussion of NeRF algorithms
|
| May 10 |
|
|
Discussion of the render arc of NeRF papers + review of the 3D rasterization pipeline (so we can talk about performance challenges next.)
|
| May 12 |
|
|
Scheduling graphics pipeline onto parallel GPUs, key optimizations for modern, power-optimized mobile GPUs.
|
| May 17 |
|
|
Motivations of ray tracing, ray tracing workload characteristics, memory coherence and SIMD execution challenges of ray tracing, modern hardware acceleration on NVIDIA RTX GPUs)
|
| May 19 |
|
|
Efficient BVH construction, hardware-accelerated ray tracing APIs, neural denoising and post-processing techniques.
|
| May 24 |
|
|
Epic’s Nanite Renderer (Guest Lecture: Brian Karis - Epic Games)
Brian Karis will talk about the design of Epic's Nanite renderer (efficient real-time rendering of very high-resolution geometry)
|
| May 26 |
|
|
How might systems for rendering and simulating virtual worlds be architected differently to support the needs of training machines instead of playing video games? (a.k.a. rendering for machine eyes, not human eyes)
|
| May 31 |
|
|
The Slang Shading Language (Guest Lecture: Yong He and Teresa Foley - NVIDIA)
The design and implementation of Slang, discussion about transferring academic systems research into industry efforts.
|
| Jun 02 |
|
|
Compute Challenges at Waymo (Guest Lecture: Daniel Rosenband and Solomon Boulos - Waymo)
On-vehicle sensing technologies and CPU/GPU/ML accelerator compute challenges in the real-time AV setting, challenges of AV simulation, such as accuracy vs. compute cost tradeoffs.
|
In addition to expectation that all students attend and participate in discussions in live lecture, there will be two short programming assignments and a self-selected term project.
| Apr 18 | Burst Mode HDR Camera RAW Processing |
| Apr 29 | Scheduling a DNN Conv Layer (Making Students Appreciate cuBLAS) |
| Jun 3 | Term Project |