summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/Vectorize/VecUtils.cpp
Commit message (Collapse)AuthorAgeFilesLines
* SLPVectorizer: Change the order in which new instructions are added to the ↵Nadav Rotem2013-05-221-51/+110
| | | | | | | | | | | | function. We are not working on a DAG and I ran into a number of problems when I enabled the vectorizations of 'diamond-trees' (trees that share leafs). * Imroved the numbering API. * Changed the placement of new instructions to the last root. * Fixed a bug with external tree users with non-zero lane. * Fixed a bug in the placement of in-tree users. llvm-svn: 182508
* Suppress GCC compiler warnings in release builds about variables that are onlyDuncan Sands2013-05-131-0/+1
| | | | | | read in asserts. llvm-svn: 181689
* SLPVectorizer: Swap LHS and RHS. No functionality change.Nadav Rotem2013-05-131-4/+4
| | | | llvm-svn: 181684
* SLPVectorizer: Fix a bug in the code that generates extracts for values with ↵Nadav Rotem2013-05-121-7/+27
| | | | | | | | multiple users. The external user does not have to be in lane #0. We have to save the lane for each scalar so that we know which vector lane to extract. llvm-svn: 181674
* SLPVectorizer: Clear the map that maps between scalars to vectors after each ↵Nadav Rotem2013-05-121-0/+1
| | | | | | | | round of vectorization. Testcase in the next commit. llvm-svn: 181673
* SLPVectorizer: Add support for trees with external users.Nadav Rotem2013-05-101-9/+50
| | | | | | | | | | | | | For example: bar() { int a = A[i]; int b = A[i+1]; B[i] = a; B[i+1] = b; foo(a); <--- a is used outside the vectorized expression. } llvm-svn: 181648
* SLPVectorize: Add support for vectorization of casts.Nadav Rotem2013-04-211-0/+69
| | | | llvm-svn: 179975
* SLPVectorizer: Fix a bug in the code that scans the tree in search of nodes ↵Nadav Rotem2013-04-211-0/+1
| | | | | | | | with multiple users. We did not terminate the switch case and we executed the search routine twice. llvm-svn: 179974
* VecUtils: Clean up uses of dyn_cast.Benjamin Kramer2013-04-201-4/+4
| | | | llvm-svn: 179936
* SLPVectorizer: Strength reduce SmallVectors to ArrayRefs.Benjamin Kramer2013-04-201-12/+12
| | | | | | Avoids a couple of copies and allows more flexibility in the clients. llvm-svn: 179935
* SLPVectorizer: Improve the cost model for loop invariant broadcast values.Nadav Rotem2013-04-201-8/+23
| | | | llvm-svn: 179930
* Fix the header comment.Nadav Rotem2013-04-201-1/+1
| | | | llvm-svn: 179928
* Use 64bit arithmetic for calculating distance between pointers.Nadav Rotem2013-04-201-2/+2
| | | | llvm-svn: 179927
* SLPVectorizer: Make it a function pass and add code for hoisting the ↵Nadav Rotem2013-04-151-1/+8
| | | | | | vector-gather sequence out of loops. llvm-svn: 179562
* SLP: Document the scalarization cost method.Nadav Rotem2013-04-141-3/+10
| | | | llvm-svn: 179479
* SLPVectorizer: Add support for trees that don't start at binary operators, ↵Nadav Rotem2013-04-141-0/+10
| | | | | | and add the cost of extracting values from the roots of the tree. llvm-svn: 179475
* SLPVectorizer: add initial support for reduction variable vectorization.Nadav Rotem2013-04-141-0/+10
| | | | llvm-svn: 179470
* SLPVectorizer: add support for vectorization of diamond shaped trees. We now ↵Nadav Rotem2013-04-121-35/+207
| | | | | | perform a preliminary traversal of the graph to collect values with multiple users and check where the users came from. llvm-svn: 179414
* We require DataLayout for analyzing the size of stores.Nadav Rotem2013-04-101-1/+1
| | | | llvm-svn: 179206
* Add support for bottom-up SLP vectorization infrastructure.Nadav Rotem2013-04-091-0/+439
This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } llvm-svn: 179117
OpenPOWER on IntegriCloud