From b5a8a905ae58cb1019080f97130890e554afb852 Mon Sep 17 00:00:00 2001 From: Nadav Rotem Date: Wed, 26 Jun 2013 17:59:35 +0000 Subject: [PATCH] The SLP Vectorizer works across basic blocks. Update the docs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184973 91177308-0d34-0410-b5e6-96231b3b80d8 --- docs/Vectorizers.rst | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/docs/Vectorizers.rst b/docs/Vectorizers.rst index d565c2122c9..221fb2949f8 100644 --- a/docs/Vectorizers.rst +++ b/docs/Vectorizers.rst @@ -7,11 +7,11 @@ Auto-Vectorization in LLVM LLVM has two vectorizers: The :ref:`Loop Vectorizer `, which operates on Loops, and the :ref:`SLP Vectorizer -`, which optimizes straight-line code. These vectorizers +`. These vectorizers focus on different optimization opportunities and use different techniques. The SLP vectorizer merges multiple scalars that are found in the code into -vectors while the Loop Vectorizer widens instructions in the original loop -to operate on multiple consecutive loop iterations. +vectors while the Loop Vectorizer widens instructions in loops +to operate on multiple consecutive iterations. .. _loop-vectorizer: @@ -302,10 +302,9 @@ Details ------- The goal of SLP vectorization (a.k.a. superword-level parallelism) is -to combine similar independent instructions within simple control-flow regions -into vector instructions. Memory accesses, arithemetic operations, comparison -operations and some math functions can all be vectorized using this technique -(subject to the capabilities of the target architecture). +to combine similar independent instructions +into vector instructions. Memory accesses, arithmetic operations, comparison +operations, PHI-nodes, can all be vectorized using this technique. For example, the following function performs very similar operations on its inputs (a1, b1) and (a2, b2). The basic-block vectorizer may combine these @@ -318,8 +317,7 @@ into vector operations. A[1] = a2*(a2 + b2)/b2 + 50*b2/a2; } -The SLP-vectorizer has two phases, bottom-up, and top-down. The top-down vectorization -phase is more aggressive, but takes more time to run. +The SLP-vectorizer processes the code bottom-up, across basic blocks, in search of scalars to combine. Usage ------ -- 2.34.1