PODCAST
[Audio] Illinois ECE 498AL: Programming Massively Parallel Processors
by Wen-Mei W Hwu
Spring 2009 Virtually all semiconductor market domains, including PCs, game consoles, mobile handsets, servers, supercomputers, and networks, are converging to concurrent platforms. There are two important reasons for this trend. First, these concurrent processors can potentially offer more...
Episodes
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 13: Reductions and their Implementation
Structuring Parallel AlgorithmsTopics: Parallel Reductions Parallel Prefix Sum Relevance of Scan Application of Scan Scan on the CPU First attempt Parallel Scan Algorithm Work efficiency considerations Improving Efficiency Use Padding to reduce conflicts Global Synchronization in CUDAThese…
more -
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 12: Structuring Parallel Algorithms
Structuring Parallel AlgorithmsTopics: Key Parallel Programming Steps Algorithms Choosing Algorithm Structure Mapping a Divide and Conquer algorithm Tiled Algorithms Increased work per thread Double Buffering Loop Fusion and Memory Privatization Pipeline or "Spatial Computing Model" These lecture...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 11: Floating Point Considerations
Floating Point ConsiderationsTopics: GPU Floating Point Features Normalized Representation Exponent Representation Representable Numbers Flush to Zero Denormaliztion Runtime Math library Make Your Programs Float Safe! These lecture were breezed by Carl Pearson and Daniel Borup and then reviewed,...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 10: Control Flow
Control FlowTopics: Terminology Review How Thread Blocks are Partitioned Control Flow Instructions Parallel Reduction A Vector Reduction Example A simple Implementation Vector Reduction With Bank Conflicts Vector Reduction With Branch Divergence Predicted Execution Concept Instruction Prediction…
more -
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 9: Memory Hardware in G80
Memory Hardware in G80Topics: CUDA Device Memory Space Parallel Memory Sharing SM Memory Architecture SM Register File Programmer view of Register File Matrix Multiplication Example More on Dynamic Partitioning ILP vs. TLP Memory Layout of a Matrix in C Constants Shared Memory Parallel Memory...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 8: Threading Hardware in G80
Threading Hardware in G80Topics: Single Program Multiple Data (SPMD) Grids and Blocks CUDA Thread Block : Review Geforce-8 Series Hardware Overview CUDA Processor Terminology Stream Multiprocesor (SM) G80 Thread Computing Pipeline Thread Lifecycle in Hardware SM Executes Blocks Thread Scheduling...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 7: GPU as part of the PC Architecture
GPU as part of the PC ArchitectureTopics: Typical Structure of a CUDA Program Bandwidth: Gravity of Modern computer Systems (Original) PCI Bus Specification PCI as Memory Mapped I/O PCI Express (PCI-E) PCI-E Links and Lanes PCI-E PC Architecture Intel Single Core System Intel Dual Core System AMD...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 6: CUDA Memories - Part 2
CUDA Memories Part2Topics: Tiled Multiply Breaking Md and Nd into Tiles Tiled Matrix Multiplication Kernel CUDA Code - Kernel Execution Configuration First Order Size considerations in G80 G80 Shared Memory and Threading Tiling Size Effects Typical Structure of a CUDA ProgramThese lecture were...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 5: CUDA Memories
CUDA MemoriesTopics: G80 Implementation of CUDA Memories CUDA Variable Type Qualifiers Where to Declare Variables Variable Type Restrictions A Common Programming Strategy GPU Atomic Integer Operations Matrix Multiplication Using Shared Memory How About performance on G80? IDEA: Use Shared Memory…
more -
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 4: CUDA Threads - Part 2
CUDA Threads Part2Topics: CUDA Thread Block Transparent Scalability G80 CUDA Mode, A Review Executing Thread Blocks Thread Scheduling Block Granularity Considerations More Details of API Features Application Programming Interface Language Extensions: Built-in Variables Common Runtime Component:...
-
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 3: CUDA Threads, Tools, Simple Examples
CUDA Threads, Tools, Simple ExamplesTopics: A Running example of Matrix Multiplication Memory Layout of a Matrix in C Compiling a CUDA Program Device Emulation Mode Pitfalls Floating Point CUDA Threads MAtrix Multiplication Using Multiple Blocks Transparent ScalabilityThese lecture were breezed…
more -
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 2: The CUDA Programming Model
CUDA Programming ModelTopics: What is GPGPU? CUDA An Example of Physical Reality Behind CUDA Parallel computing on a GPU CUDA - C With no shader limitations CUDA Devices and Threads G80 Graphics Mode G80 CUDA Mode Arrays of Parallel Threads Thread Blocks, Scalable Cooperation Block ID's and…
more -
Illinois ECE 498AL: Programming Massively Parallel Processors, Lecture 1: Introduction
Programming Massively Parallel ProcessorsTopics: Introduction, Grading, Outline Lab Equipment UIUC/NCSA QP Cluster UIUC/NCSA AP Cluster ECE498AL Development History Why Program Massively Parallel Processors? Geforce 8800 G80 Characteristics Future Apps reflect a concurrent world Stretching...
We're indexing this podcast's transcripts for the first time — this can take a minute or two. We'll show results as soon as they're ready.
No matches for "" in this podcast's transcripts.
No topics indexed yet for this podcast.
Loading reviews...
ABOUT THIS SHOW
Spring 2009 Virtually all semiconductor market domains, including PCs, game consoles, mobile handsets, servers, supercomputers, and networks, are converging to concurrent platforms. There are two important reasons for this trend. First, these concurrent processors can potentially offer more...
HOSTED BY
Wen-Mei W Hwu
Loading similar podcasts...
Frequently Asked Questions
How many episodes does [Audio] Illinois ECE 498AL: Programming Massively Parallel Processors have?
[Audio] Illinois ECE 498AL: Programming Massively Parallel Processors currently has 13 episodes available on PodParley. New episodes are automatically indexed when they're published to the podcast feed.
What is [Audio] Illinois ECE 498AL: Programming Massively Parallel Processors about?
Spring 2009 Virtually all semiconductor market domains, including PCs, game consoles, mobile handsets, servers, supercomputers, and networks, are converging to concurrent platforms. There are two important reasons for this trend. First, these concurrent processors can potentially offer more...
How often does [Audio] Illinois ECE 498AL: Programming Massively Parallel Processors release new episodes?
[Audio] Illinois ECE 498AL: Programming Massively Parallel Processors has 13 episodes. Check the episode list to see recent publication dates and frequency.
Where can I listen to [Audio] Illinois ECE 498AL: Programming Massively Parallel Processors?
You can listen to [Audio] Illinois ECE 498AL: Programming Massively Parallel Processors on PodParley by clicking any episode. We provide an embedded audio player for direct listening, and you can also subscribe via your preferred podcast app using the RSS feed.
Who hosts [Audio] Illinois ECE 498AL: Programming Massively Parallel Processors?
[Audio] Illinois ECE 498AL: Programming Massively Parallel Processors is created and hosted by Wen-Mei W Hwu.
URL copied to clipboard!