Our great sponsors
-
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
-
AdaptiveCpp
Implementation of SYCL and C++ standard parallelism for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous programming models. Lets applications adapt themselves to all the hardware in the system - even at runtime!
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
I thought I'd share something with my experience with HPC that applies to many areas, especially in the rise of GPUs.
The main bottleneck isn't compute, it is memory. If you go to talks you're gonna see lots of figures like this one[0] (typically also showing disk speeds, which are crazy small).
Compute is increasing so fast that at this point we finish our operations long faster than it takes to save those simulations or even create the visualizations and put on disk. There's a lot of research going into this, with a lot of things like in situ computing (asynchronous operations, often pushing to a different machine, but needing many things like flash buffers. See ADIOS[1] as an example software).
What I'm getting at here is that we're at a point where we have to think about that IO bottleneck, even for non-high performance systems. I work in ML now, which we typically think of as compute bound, but being in the generative space there are still many things where the IO bottlenecks. This can be loading batches into memory, writing results to disk, or communication between distributed processes. It's one beg reason we typically want to maximize memory usage (large batches).
There's a lot of low hanging fruit in these areas that aren't going to be generally publishable works but are going to have lots of high impact. Just look at things like LLaMA CPP[2], where in the process they've really decreased the compute time and memory load. There's also projects like TinyLLaMa[3] who are exploring training a 1B model and doing so on limited compute, and are getting pretty good results. But I'll tell you from personal experience, small models and limited compute experience doesn't make for good papers (my most cited work did this and has never been published, gotten many rejections for not competing with models 100x it's size, but is also quite popular in the general scientific community who work with limited compute). Wfiw, companies that are working on applications do value these things, but it is also noise in the community that's hard to parse. Idk how we can do better as a community to not get trapped in these hype cycles, because real engineering has a lot of these aspects too, and they should be (but aren't) really good areas for academics to be working in. Scale isn't everything in research, and there's a lot of different problems out there that are extremely important but many are blind to.
And one final comment, there's lots of code that is used over and over that are not remotely optimized and can be >100x faster. Just gotta slow down and write good code. The move fast and break things method is great for getting moving but the debt compounds. It's just debt is less visible, but there's so much money being wasted from writing bad code (and LLMs are only going to amplify this. They were trained on bad code after all)
[0] https://drivenets.com/wp-content/uploads/2023/05/blog-networ...
[1] https://github.com/ornladios/ADIOS2
[2] https://github.com/ggerganov/llama.cpp
[3] https://github.com/jzhang38/TinyLlama
I thought I'd share something with my experience with HPC that applies to many areas, especially in the rise of GPUs.
The main bottleneck isn't compute, it is memory. If you go to talks you're gonna see lots of figures like this one[0] (typically also showing disk speeds, which are crazy small).
Compute is increasing so fast that at this point we finish our operations long faster than it takes to save those simulations or even create the visualizations and put on disk. There's a lot of research going into this, with a lot of things like in situ computing (asynchronous operations, often pushing to a different machine, but needing many things like flash buffers. See ADIOS[1] as an example software).
What I'm getting at here is that we're at a point where we have to think about that IO bottleneck, even for non-high performance systems. I work in ML now, which we typically think of as compute bound, but being in the generative space there are still many things where the IO bottlenecks. This can be loading batches into memory, writing results to disk, or communication between distributed processes. It's one beg reason we typically want to maximize memory usage (large batches).
There's a lot of low hanging fruit in these areas that aren't going to be generally publishable works but are going to have lots of high impact. Just look at things like LLaMA CPP[2], where in the process they've really decreased the compute time and memory load. There's also projects like TinyLLaMa[3] who are exploring training a 1B model and doing so on limited compute, and are getting pretty good results. But I'll tell you from personal experience, small models and limited compute experience doesn't make for good papers (my most cited work did this and has never been published, gotten many rejections for not competing with models 100x it's size, but is also quite popular in the general scientific community who work with limited compute). Wfiw, companies that are working on applications do value these things, but it is also noise in the community that's hard to parse. Idk how we can do better as a community to not get trapped in these hype cycles, because real engineering has a lot of these aspects too, and they should be (but aren't) really good areas for academics to be working in. Scale isn't everything in research, and there's a lot of different problems out there that are extremely important but many are blind to.
And one final comment, there's lots of code that is used over and over that are not remotely optimized and can be >100x faster. Just gotta slow down and write good code. The move fast and break things method is great for getting moving but the debt compounds. It's just debt is less visible, but there's so much money being wasted from writing bad code (and LLMs are only going to amplify this. They were trained on bad code after all)
[0] https://drivenets.com/wp-content/uploads/2023/05/blog-networ...
[1] https://github.com/ornladios/ADIOS2
[2] https://github.com/ggerganov/llama.cpp
[3] https://github.com/jzhang38/TinyLlama
I thought I'd share something with my experience with HPC that applies to many areas, especially in the rise of GPUs.
The main bottleneck isn't compute, it is memory. If you go to talks you're gonna see lots of figures like this one[0] (typically also showing disk speeds, which are crazy small).
Compute is increasing so fast that at this point we finish our operations long faster than it takes to save those simulations or even create the visualizations and put on disk. There's a lot of research going into this, with a lot of things like in situ computing (asynchronous operations, often pushing to a different machine, but needing many things like flash buffers. See ADIOS[1] as an example software).
What I'm getting at here is that we're at a point where we have to think about that IO bottleneck, even for non-high performance systems. I work in ML now, which we typically think of as compute bound, but being in the generative space there are still many things where the IO bottlenecks. This can be loading batches into memory, writing results to disk, or communication between distributed processes. It's one beg reason we typically want to maximize memory usage (large batches).
There's a lot of low hanging fruit in these areas that aren't going to be generally publishable works but are going to have lots of high impact. Just look at things like LLaMA CPP[2], where in the process they've really decreased the compute time and memory load. There's also projects like TinyLLaMa[3] who are exploring training a 1B model and doing so on limited compute, and are getting pretty good results. But I'll tell you from personal experience, small models and limited compute experience doesn't make for good papers (my most cited work did this and has never been published, gotten many rejections for not competing with models 100x it's size, but is also quite popular in the general scientific community who work with limited compute). Wfiw, companies that are working on applications do value these things, but it is also noise in the community that's hard to parse. Idk how we can do better as a community to not get trapped in these hype cycles, because real engineering has a lot of these aspects too, and they should be (but aren't) really good areas for academics to be working in. Scale isn't everything in research, and there's a lot of different problems out there that are extremely important but many are blind to.
And one final comment, there's lots of code that is used over and over that are not remotely optimized and can be >100x faster. Just gotta slow down and write good code. The move fast and break things method is great for getting moving but the debt compounds. It's just debt is less visible, but there's so much money being wasted from writing bad code (and LLMs are only going to amplify this. They were trained on bad code after all)
[0] https://drivenets.com/wp-content/uploads/2023/05/blog-networ...
[1] https://github.com/ornladios/ADIOS2
[2] https://github.com/ggerganov/llama.cpp
[3] https://github.com/jzhang38/TinyLlama
Also check out this talk and slides from few years ago about CPU and GPU nitpicks
Alexander Titov — Know your hardware: CPU memory hierarchy https://youtu.be/QOJ2hsop6hM
https://github.com/alexander-titov/public/blob/master/confer... Your Hardware - CPU Memory Hierarchy -- Alexander Titov -- C%2B%2B Moscow Meetup March 2019.pdf
https://github.com/alexander-titov/public/blob/master/confer... - what it is and why you should care -- Alexander Titov -- CoreHard 2019.pdf
Sapphire Rapids is a CPU.
AMD's primary focus for a GPU software ecosystem these days seems to be implementing CUDA with s/cuda/hip, so AMD directly supports and encourages running GPU software written in CUDA on AMD GPUs.
The only implementation for sycl on AMD GPUs that I can find is a hobby project that apparently is not allowed to use either the 'hip' or 'sycl' names. https://github.com/AdaptiveCpp/AdaptiveCpp
Related posts
- Offloading standard C++ PSTL to Intel, NVIDIA and AMD GPUs with AdaptiveCpp
- AMD's HIPRT Working Its Way To Blender With ~25% Faster Rendering
- How to install OpenCL for AMD CPU?
- hipSYCL can now generate a binary that runs on any Intel/NVIDIA/AMD GPU - in a single compiler pass. It is now the first single-pass SYCL compiler, and the first with unified code representation across backends.
- Bringing Nvidia® and AMD support to oneAPI