mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-09-27 16:17:17 +00:00
Include blurb about Likely. By Josh Klontz.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_35@216762 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
@@ -305,6 +305,21 @@ which ensure vector-friendly data layout, explicit vectorization and compact
|
|||||||
representation of the program. The project uses the LLVM infrastructure for
|
representation of the program. The project uses the LLVM infrastructure for
|
||||||
optimization and code generation.
|
optimization and code generation.
|
||||||
|
|
||||||
|
Likely
|
||||||
|
------
|
||||||
|
|
||||||
|
`Likely <http://www.liblikely.org>`_ is an embeddable just-in-time Lisp for
|
||||||
|
image recognition and heterogenous architectures. Algorithms are just-in-time
|
||||||
|
compiled using LLVM’s MCJIT infrastructure to execute on single or
|
||||||
|
multi-threaded CPUs and potentially OpenCL SPIR or CUDA enabled GPUs. Likely
|
||||||
|
exploits the observation that while image processing and statistical learning
|
||||||
|
kernels must be written generically to handle any matrix datatype, at runtime
|
||||||
|
they tend to be executed repeatedly on the same type. Likely also seeks to
|
||||||
|
explore new optimizations for statistical learning algorithms by moving them
|
||||||
|
from an offline model generation step to a compile-time simplification of a
|
||||||
|
function (the learning algorithm) with constant arguments (the training set).
|
||||||
|
|
||||||
|
|
||||||
Additional Information
|
Additional Information
|
||||||
======================
|
======================
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user