Compilers and More: GPU Architecture and Applications

By Michael Wolfe

September 10, 2008

One of the most exciting developments in parallel programming over the past few years has been the availability and advancement of programmable graphics cards. A high end graphics card costs less than a high end CPU and provides tantalizing peak performance approaching, or exceeding, one teraflop. Since microprocessor peak performance tops out at about 25 gigaflops/core (single precision), this potential, at such low cost, is worth exploring. Harnessing this performance, however, is problematic.

It’s important to note that the GPUs powering the graphics cards are designed to do specific jobs very well. They are not designed as general purpose processors, and in fact will do a very poor job on many programs, even highly parallel applications. The key is to determine whether your application can fit into a programming model that maps well onto the GPU. I’m going to discuss the GPU architecture, but I’m going to start with an analogy, and probably stretch the analogy to the breaking point; let’s discuss airline travel.

Suppose your job is to transport several dozen large tour groups between London and Seattle, each group with 30-60 members. Your most likely choice is to use jet aircraft for a flight of about 5,000 miles or 7,700 km. Going for the most parallelism, you could use a new Airbus A380 to move 600 people in about 9 hours. One problem you have with these jumbo jets is they don’t fit at the main terminal, so you have to take an airport train out to the remote terminal where the plane is parked; the train can only carry so many people at a time, but let’s be optimistic and say it will take 90 minutes to move everyone out to the remote gate and load them, and another 90 minutes at the other end for unloading. This gives us a 24 hour round trip. If you regularly fill the plane, this could be a good investment (though, at $300M, a bit more than a GPU). However, if you only have a half-load, it doesn’t get them there twice as fast or at half the cost, though it does reduce the load/unload time. Measuring performance as passenger-miles, the performance comes from parallelism (many passengers), not from latency reduction.

Alternatively, you could opt for a few smaller planes, say two to four Boeing 787s. Each can carry about 200-250 passengers at the same speed, so you can move the same number of people at the same rate. You also have the advantage of parking at the main terminal, so you can reduce the passenger load/unload time to about half an hour, so your total round trip time is only 20 hours. Of course, you have to arrange for more crew, more landing slots at the airports, and so forth. Your total capital investment is about the same, but it gives you some flexibility. If you only have 200 people to move, you can leave all but one of the planes behind, saving on fuel and crew costs.

Or, perhaps you could invest in the (future) hypersonic transport, which some believe may be able to travel at speeds of Mach 6, 7-8 times faster than the current subsonic airliners. Assuming it takes time to get up to speed and to slow down for landing, the total flight time might drop from 9 hours to 2.5 hours, or 7 hours round trip. If the capacity of your hypothetical hypersonic transport is 200 passengers, you can transport 600 people in each direction in just 21 hours. Even better, if you only have to transport 400 people, you can get the same work done in two-thirds the time. Of course, you are buying a higher cost transport, probably paying more for fuel, and so on.

Very fast CPUs are more like the hypersonic transport; they are designed to provide extremely high performance for small tasks, but still offer adequate performance for large tasks. Multicore processors are more like the middle option, several smaller, lower-capacity devices, each quite capable, and you can save power by shutting down one or more of them. The GPU is more like the super-jumbo jet; it only gets high performance (passenger-miles) when you have lots of passengers. It doesn’t do so well getting just one or a few passengers across the ocean.

Thread Execution Control Unit

So now to GPU architecture. GPUs were originally hardwired for specific tasks; as transistor budgets and demand for flexibility grew, the hardware became more programmable. They still contain special hardware and functional units specific to graphics tasks, but I’ll ignore those and view today’s GPUs as compute accelerators. A typical design, shown in the figure above, is abstracted from information put out by NVIDIA. I’ll use both NVIDIA’s terms and more standard computer architecture descriptions of the various parts. The key to the performance is all those thread processors; in the figure, there are eight thread processors in each of 16 multiprocessors, for 128 TPs total. NVIDIA delivers GPUs with up to 30 multiprocessors and 240 TPs. In each clock, each TP can produce a result, giving this design a very high peak performance rating.

Each multiprocessor executes in SIMD mode, meaning each thread processor in that multiprocessor executes the same instruction simultaneously. If one thread processor is executing a floating point add, they all are; if one is doing a fetch, they all are. Moreover, each instruction is quad-clocked, meaning the SIMD width is 32, even though there are only eight thread processors. Unlike classical SIMD machines, there isn’t a distinction between the scalar and parallel operations, or mono and poly operations, to borrow terms from C* and Dataparallel C, and Cn for the Clearspeed card. Instead, the model is that of many scalar threads that just happen to be executing in SIMD mode, something NVIDIA calls SIMT execution. Careful orchestration of the 32 threads that execute in SIMD mode is necessary for best performance.

Stretching our analogy, think of each thread processor like a seat in our superjumbo jet, and each multiprocessor as a tour group. Imagine that when the flight attendant serves a meal, the whole tour group must be served at once (synchronously). The whole tour group must watch the same movie on the seat-back screens at the same time, or they all must read books at the same time, though some may be napping at any time. When one person wants to use the restroom, they all must go at once, even if not everyone needs to. Note that this is a long latency operation, which will correspond to the long latency memory.

The multiprocessors themselves execute asynchronously, and without communication. This last point is quite important. In a multicore or multiprocessor system, the cores or processors can communicate through the memory. If one thread stores a value in variable A then sets a FLAG, the hardware will guarantee that another thread on the same or another core or processor will not see the updated FLAG without seeing the updated value for A. The hardware supports a memory model that preserves the store order. No such memory model is supported on the GPU; a program could store a set of values on one multiprocessor and read the same locations on another, but there is no guarantee that the value fetched will be consistent (in the formal sense) with the values stored. Relaxing the memory model allows the hardware to reorder the stores from a multiprocessor, allowing more throughput.

In this GPU, each multiprocessor has a special function unit, which handles infrequent, expensive operations, like divide, square root, and so on; it operates more slowly than other operations, but since it’s infrequently used, it doesn’t affect performance. There is a high bandwidth, low latency local memory attached to each multiprocessor. The threads executing on that multiprocessor can communicate among themselves using this local memory. In the current NVIDIA generation, the local memory is quite small (16KB).

There is also a large global device memory (over 1GB in some models). This is physical, not virtual; paging is not supported, so all the data has to fit in the memory. The device memory has very high bandwidth, but high latency to the multiprocessors. The device memory is not directly accessible from the host, nor is the host memory directly visible to the GPU. Data from the host that needs to be processed by the GPU must be moved via DMA (across the IO bus) from the host to the device memory, and the results moved back — like loading jumbo jets using thin airport trains.

So, there is a hierarchy of parallelism on this GPU; threads executing within a multiprocessor can share and communicate using the local memory, while threads executing on different multiprocessors cannot communicate or synchronize. This hierarchy is explicit in the programming model as well. Parallelism comes in two flavors; outer, asynchronous parallelism between thread groups or thread blocks, and inner, synchronous parallelism within a thread block. All the threads of a thread block will always be assigned as a group to a single multiprocessor, while different thread blocks can be assigned to different multiprocessors.

Because of the high latency to the device memory, the multiprocessors are highly multithreaded as well. When one set of SIMD threads executes a memory operation, rather than stall, the multiprocessor will switch to execute another set of SIMD threads. The other SIMD threads may be part of the same thread block, or may come from a different thread block assigned to the same multiprocessor. Think of this as the flight attendant serving another tour group while one group gets up to visit the restrooms.

This GPU is designed as a throughput engine; it’s designed to get a lot of work done on a lot of data, all very quickly, all in parallel (lots of tour groups flying in the same direction). To get high performance, your program needs enough parallelism to keep the thread processors busy (lots of customers). Each of your thread blocks needs enough parallelism to fill all the thread processors in a multiprocessor (big tour groups), and at least as many thread blocks as you have multiprocessors (many big tour groups). In addition, you need even more parallelism to keep the multiprocessors busy when they need to thread-switch past a long latency memory operation (many many big tour groups).

However, lots of parallelism isn’t quite sufficient. The GPU is designed for structured data accesses, which graphic processing naturally uses. (Here’s where my analogy falls apart.) The memory is designed for efficient access to contiguous blocks of memory, meaning adjacent threads using adjacent data. Your program will run noticeably slower if it does random memory fetches, or (shades of vector processing) simultaneous accesses to the same memory bank. But if your program is structured to use contiguous data, the memory can run at full bandwidth.

The program model reflects this structure as well. Consider a simple graphics shader; you want to compute the color at each pixel on the screen. Generally, the color at each pixel is more or less independent of the color at every other pixel (natural parallelism), and the problem has a natural index set (the two-dimensional pixel coordinate). So the program model is a scalar program to be executed at each pixel coordinate, replicated and parallelized over the index set. The scalar program is a kernel and the index set is the domain. The indices for each instance of the kernel determine which pixel is being processed and are used to fetch and store data.

When you write a general purpose program for a GPU, you must currently follow this model as well. You must split out the computational kernels and the corresponding domains. You have to identify which data will live in the local memory, and move data between the local and device memory, keeping in mind that the local memory data only has a lifetime of a thread block.

Each kernel will complete its entire domain before the next kernel starts. In our airline analogy, you have to complete the eastbound flight for all the tour groups on board before starting the next flight westbound. The parallelism comes from the domain of a single kernel (data parallelism, all tour groups flying East at the same time), not from running many different kernels at once (task parallelism, lots of tour groups flying all over the country or world at once). This naturally limits, or focuses users on, the applications for which a GPU is appropriate.

Another key difference between GPUs and more general purpose multicore processors is hardware support for parallelism. GPUs don’t try to address all the possible forms of parallelism, but they do solve their target range quite well. We’ve already mentioned the SIMD instruction sets within a multiprocessor and hardware multithreading. There is also a hardware thread control unit that manages the distribution and assignment of thread blocks to multiprocessors. There is additional hardware support for synchronization within a thread block. Your common multicore processor depends on software and the OS to provide these features, so GPU has an advantage.

Programming GPUs Today

So far I haven’t really discussed how these highly parallel GPU architectures are programmed. Past accelerators were often programmed by offloading functions or subroutines; the user or compiler would marshall the arguments, send them to the accelerator, launch the function on the accelerator, and wait for completion, perhaps doing other useful work in the meantime. GPUs don’t fit this model; they aren’t fully functional, separately programmable devices. They really can only execute kernels, comprising a scalar kernel program and an index domain over which to apply it. If your function were that simple (matrix multiplication, SGEMM), it could look like a subroutine engine. Anything more complex, and the host has to manage the GPU execution by selecting and ordering a sequence of kernels to execute, and performing any scalar operations and conditionals along the way. In my next column, I’ll discuss the sometimes superhuman efforts necessary to decompose a program into kernels and manage the data movement between the host and the GPU.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire