Close to Metal

In computing, Close To Metal ("CTM" in short, originally called Close-to-the-Metal) is the name of a beta version of a low-level programming interface developed by ATI, now the AMD Graphics Product Group, aimed at enabling GPGPU computing. CTM was short-lived, and the first production version of AMD's GPGPU technology is now called AMD Stream SDK, or rather the current AMD APP SDK for Windows and Linux 32-bit and 64-bit. APP stands for "Accelerated Parallel Processing"[1] and also targets Heterogeneous System Architecture.[citation needed]

Overview

Close To Metal, originally called THIN (Thin Hardware INterface) and Data Parallel Virtual Machine, gave developers direct access to the native instruction set and memory of the massively parallel computational elements in modern AMD video cards. CTM bypassed the graphics-centric DirectX and OpenGL APIs for the GPGPU programmer to expose previously unavailable low-level functionality, including direct control of the stream processors/ALUs and the memory controllers. R580 (ATI X1900) and later generations of AMD's GPU microarchitecture supported the CTM interface.

CTM's commercial successor, AMD Stream SDK, was released under AMD EULA in December 2007 after the software stack was rewritten.[2] Stream SDK provides high-level in addition to low-level tools for general-purpose access to AMD graphics hardware.

Using GPUs to perform computations holds a lot of potential for some applications because of the fundamental differences of GPU microarchitectures compared to CPUs. GPUs achieve much greater throughput (calculations per second) by executing many programs in parallel and restricting flow control (the ability of one program to execute instructions independently of another). Modern GPUs also have addressable on-die memory and extremely high performance multi-channel external memory.

AMD subsequently switched from CTM to OpenCL.[3]

Open-source

Some components of CTM and the Stream SDK are open source, such as the Brook+ C-like language and compiler.

See also

  • ROCm
  • CUDA
  • BrookGPU
  • Lib Sh
  • Stream programming
  • Shader

References

  1. ^ "AMD APP SDK OpenCL™ Accelerated Parallel Processing". Archived from the original on 2014-07-01. Retrieved 2014-07-06.
  2. ^ AMD Stream SDK download page Archived December 23, 2007, at the Wayback Machine, retrieved June 12, 2008
  3. ^ Valich, Theo (7 August 2008). "AMD Ditches Close-To-Metal, Focuses On DX11 And OpenCL". Tom's Hardware. Retrieved 13 September 2017.
Notes
  • ^ AMD “Close to Metal” Technology Unleashes the Power of Stream Computing: AMD Press Release, November 14, 2006.
  • ^ AnandTech report: ATI's Stream Processing & [email protected], September 30, 2006.
  • ^ Universität Dortmund, Fachbereich Mathematik research: Accelerating Double precision on GPUs (Proceedings of ASIM 2005), Dominik Goddeke, Robert Strzodka, and Stefan Turek. 18th Symposium on Simulation Technique, 2005.[dead link]
  • ^ TGDaily report: Nvidia activates a supercomputer in your PC, February 16, 2007.

External links

  • ATI official site* AMD official website
  • "ATI DPVM SIGGRAPH 2006 sketch" (PDF). Archived from the original (PDF) on 2007-09-27. (134 KiB)
  • "ATI DVPM SIGGRAPH 2006 Presentation" (PDF). Archived from the original (PDF) on 2007-09-27. (671 KiB)
  • "CTM Guide - CTI Technical Reference Manual" (PDF). Archived from the original (PDF) on 2007-02-22. (866 KiB)
  • AMD Close-to-the-Metal (CTM) open source project site
  • v
  • t
  • e
Radeon-brand
List of GPUs (GPU features template) and List of APUs (APU features template)
Fixed pipeline
Vertex and fragment shaders
Unified shaders
TeraScale
Unified shaders & memory
GCN
RDNA
Current technologies and software
Audio/Video acceleration
GPU technologies
Software
Current
Obsolete
Other brands and products
Workstations
& Supercomputers
Current
Obsolete
Consoles
& Handheld PCs