1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-24 21:42:54 +02:00
Commit Graph

19 Commits

Author SHA1 Message Date
Daniel Jasper
162ffcacd6 Revert @llvm.assume with operator bundles (r289755-r289757)
This creates non-linear behavior in the inliner (see more details in
r289755's commit thread).

llvm-svn: 290086
2016-12-19 08:22:17 +00:00
Hal Finkel
f224db75d2 Remove the AssumptionCache
After r289755, the AssumptionCache is no longer needed. Variables affected by
assumptions are now found by using the new operand-bundle-based scheme. This
new scheme is more computationally efficient, and also we need much less
code...

llvm-svn: 289756
2016-12-15 03:02:15 +00:00
Adam Nemet
d6eee273b7 [LoopDataPrefetch] Port to new streaming API for opt remarks
llvm-svn: 282826
2016-09-30 00:42:43 +00:00
Balaram Makam
73565ebed9 [LoopDataPrefetch] Use range based for loop; NFCI
Switch to range based for loop.
No functional change, but more readable code.

llvm-svn: 280966
2016-09-08 17:08:20 +00:00
Teresa Johnson
8d0046afe0 [PM] Port LoopDataPrefetch to new pass manager
Summary:
Refactor the existing support into a LoopDataPrefetch implementation
class and a LoopDataPrefetchLegacyPass class that invokes it.
Add a new LoopDataPrefetchPass for the new pass manager that utilizes
the LoopDataPrefetch implementation class.

Reviewers: mehdi_amini

Subscribers: sanjoy, mzolotukhin, nemanjai, llvm-commits

Differential Revision: https://reviews.llvm.org/D23483

llvm-svn: 278591
2016-08-13 04:11:27 +00:00
Adam Nemet
0ec37e745a [LoopDataPrefetch] Fix unused variable in release build
llvm-svn: 276491
2016-07-22 23:08:10 +00:00
Adam Nemet
1c839e0506 [LoopDataPrefetch] Include hotness of region in opt remark
llvm-svn: 276488
2016-07-22 22:53:17 +00:00
Adam Nemet
22340b9cbd [LoopDataPrefetch] Sort headers
llvm-svn: 276487
2016-07-22 22:53:12 +00:00
Benjamin Kramer
eef5ae3754 Apply clang-tidy's modernize-loop-convert to most of lib/Transforms.
Only minor manual fixes. No functionality change intended.

llvm-svn: 273808
2016-06-26 12:28:59 +00:00
Nico Weber
cedbf019a4 Remove a few gendered pronouns.
llvm-svn: 272422
2016-06-10 20:06:03 +00:00
Adam Nemet
fb48dc2788 [LoopDataPrefetch] Add optimization remark
With -Rpass=loop-data-prefetch, show the memory access that got
prefetched.

llvm-svn: 268578
2016-05-05 00:08:15 +00:00
Andrew Kaylor
70edd780c7 Add opt-bisect support to additional passes that can be skipped
Differential Revision: http://reviews.llvm.org/D19882

llvm-svn: 268457
2016-05-03 22:32:30 +00:00
Adam Nemet
352693be9b [LoopDataPrefetch] Centralize the tuning cl::opts under the pass
This is effectively NFC, minus the renaming of the options
(-cyclone-prefetch-distance -> -prefetch-distance).

The change was requested by Tim in D17943.

llvm-svn: 264806
2016-03-29 23:45:52 +00:00
Adam Nemet
96b033381d [LoopDataPrefetch] Make more member functions private, NFC.
llvm-svn: 264798
2016-03-29 22:40:02 +00:00
Adam Nemet
23548e39cd [LoopDataPrefetch] Add TTI to limit the number of iterations to prefetch ahead
Summary:
It can hurt performance to prefetch ahead too much.  Be conservative for
now and don't prefetch ahead more than 3 iterations on Cyclone.

Reviewers: hfinkel

Subscribers: llvm-commits, mzolotukhin

Differential Revision: http://reviews.llvm.org/D17949

llvm-svn: 263772
2016-03-18 00:27:43 +00:00
Adam Nemet
8d7ad736df [LoopDataPrefetch/Aarch64] Allow selective prefetching of large-strided accesses
Summary:
And use this TTI for Cyclone.  As it was explained in the original RFC
(http://thread.gmane.org/gmane.comp.compilers.llvm.devel/92758), the HW
prefetcher work up to 2KB strides.

I am also adding tests for this and the previous change (D17943):

* Cyclone prefetching accesses with a large stride
* Cyclone not prefetching accesses with a small stride
* Generic Aarch64 subtarget not prefetching either

Reviewers: hfinkel

Subscribers: aemerson, rengolin, llvm-commits, mzolotukhin

Differential Revision: http://reviews.llvm.org/D17945

llvm-svn: 263771
2016-03-18 00:27:38 +00:00
Adam Nemet
65339d559f [LoopDataPrefetch] Add stats and debug output
llvm-svn: 262998
2016-03-09 05:33:21 +00:00
Adam Nemet
9244a6e185 [LoopDataPrefetch] If prefetch distance is not set, skip pass
This lets select sub-targets enable this pass.  The patch implements the
idea from the recent llvm-dev thread:
http://thread.gmane.org/gmane.comp.compilers.llvm.devel/94925

The goal is to enable the LoopDataPrefetch pass for the Cyclone
sub-target only within Aarch64.

Positive and negative tests will be included in an upcoming patch that
enables selective prefetching of large-strided accesses on Cyclone.

llvm-svn: 262844
2016-03-07 18:35:42 +00:00
Adam Nemet
27b8897111 [PPCLoopDataPrefetch] Move pass to Transforms/Scalar/LoopDataPrefetch. NFC
This patch is part of the work to make PPCLoopDataPrefetch
target-independent
(http://thread.gmane.org/gmane.comp.compilers.llvm.devel/92758).

Obviously the pass still only used from PPC at this point.  Subsequent
patches will start driving this from ARM64 as well.

Due to the previous patch most lines should show up as moved lines.

llvm-svn: 261265
2016-02-18 21:38:19 +00:00