RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
Code Issues Projects Releases Wiki Activity
42,323 Commits 4 Branches 5 Tags 704 MiB
da4e03de04
Commit Graph

42323 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Dale Johannesen
89da8440e1 When we're doing a compare of load-AND-constant to 0 
(e.g. a bitfield test) narrow the load as much as possible.
The has the potential to avoid unnecessary partial-word
load-after-store conflicts, which cause stalls on several targets.
Also a size win on x86 (testb vs testl).

llvm-svn: 58825
 2008-11-07 01:28:02 +00:00
Bill Wendling
3fe9fef0da - Modify the stack protector algorithm so that the stack slot is allocated in 
LLVM IR code and not in the selection DAG ISel. This is a cleaner solution.

- Fix the heuristic for determining if protectors are necessary. The previous
  one wasn't checking the proper type size.

llvm-svn: 58824
 2008-11-07 01:23:58 +00:00
Bill Wendling
54a5c87823 Remove unneeded header file. 
llvm-svn: 58823
 2008-11-06 23:56:59 +00:00
Bill Wendling
70e06738b4 Don't build a vector of returns. Just modify the Function in the loop. 
llvm-svn: 58822
 2008-11-06 23:55:49 +00:00
Mon P Wang
888f4e6fb0 Fixed scalarizing an extract subvector and prevent an infinite loop 
when simplify a vector. 

llvm-svn: 58820
 2008-11-06 22:52:21 +00:00
Bill Wendling
1e6576e1e0 The size limit is for individual arrays. So if any array has more than 8 bytes 
in it, then emit stack protectors.

llvm-svn: 58819
 2008-11-06 22:18:44 +00:00
Evan Cheng
3bcb71912f Encode extend instructions; more clean up. 
llvm-svn: 58818
 2008-11-06 22:15:19 +00:00
Dan Gohman
1130e8c23f Fix a use of an invalid iterator when -debug-pass=Details is used. 
llvm-svn: 58816
 2008-11-06 21:57:17 +00:00
Bill Wendling
26eadae94d Don't recalculate the stack position of the stack protector. 
llvm-svn: 58815
 2008-11-06 21:37:09 +00:00
Devang Patel
8640fd500a Emit label for llvm.dbg.func.start of the inlined function. 
llvm-svn: 58814
 2008-11-06 21:28:20 +00:00
Devang Patel
5d5357aa3b Clarify documentation. A module pass MP can require a function paqss FP only if FP does not require any module pass. 
llvm-svn: 58813
 2008-11-06 19:47:49 +00:00
Evan Cheng
af54e4ed18 - Improve naming consistency: Branch -> BrFrm, BranchMisc -> BrMiscFrm. 
- Consolidate instruction formats.
- Other clean up.

llvm-svn: 58808
 2008-11-06 17:48:05 +00:00
Evan Cheng
1ea366a419 Improve JIT debugging outputs format consistency. 
llvm-svn: 58807
 2008-11-06 17:46:04 +00:00
Nuno Lopes
e5fb2e4d84 plug leakage of mutex data. pthread_mutex_destroy() doesnt free our malloc'ed memory. 
llvm-svn: 58805
 2008-11-06 16:21:49 +00:00
Duncan Sands
50acaf2367 Formating/comment changes - no functionality change. 
llvm-svn: 58801
 2008-11-06 08:51:32 +00:00
Evan Cheng
aa24d19533 Remove opcode from instruction TS flags; add MOVCC support; fix addrmode3 encoding bug. 
llvm-svn: 58800
 2008-11-06 08:47:38 +00:00
Bill Wendling
b6e2d60e7a - Rename stackprotector_{prologue,epilogue} to stackprotector_{create,check}. 
- Get rid of "HasStackProtector" in MachineFrameInfo.
- Modify intrinsics to tell which are doing what with memory.

llvm-svn: 58799
 2008-11-06 07:23:03 +00:00
Steve Naroff
dafb062ef6 Update VC++ projects. 
llvm-svn: 58798
 2008-11-06 06:24:59 +00:00
Mon P Wang
41f90a3ee5 Widening cleanup 
llvm-svn: 58796
 2008-11-06 05:31:54 +00:00
Evan Cheng
078361bddc Handle smul<x><y>, smulw<y>, smla<x><y>, smlaw<y>. 
llvm-svn: 58793
 2008-11-06 03:35:07 +00:00
Bill Wendling
489791a127 Adjust the stack protector heuristic to care about only arrays or calls to 
"alloca".

llvm-svn: 58792
 2008-11-06 02:38:58 +00:00
Bill Wendling
08905ed703 Implement the stack protector stack accesses via intrinsics: 
- stackprotector_prologue creates a stack object and stores the guard there.

- stackprotector_epilogue reads the stack guard from the stack position created
  by stackprotector_prologue.

- The PrologEpilogInserter was changed to make sure that the stack guard is
  first on the stack frame.

llvm-svn: 58791
 2008-11-06 02:29:10 +00:00
Evan Cheng
058721d10b Fix so_imm encoding bug; add support for MOVi2pieces. 
llvm-svn: 58790
 2008-11-06 02:25:39 +00:00
Evan Cheng
ca6759021b Fix encoding of multiple instructions with 3 src operands; also handle smmul, smmla, and smmls. 
llvm-svn: 58789
 2008-11-06 01:21:28 +00:00
Evan Cheng
3e727721d0 Need a \n. 
llvm-svn: 58788
 2008-11-06 01:18:29 +00:00
Devang Patel
cea9dfa11f InstructionNamer preserves everything. 
llvm-svn: 58787
 2008-11-06 01:00:16 +00:00
Devang Patel
ec135e1f33 Emit label for llvm.dbg.func.start of the inlined function. 
llvm-svn: 58786
 2008-11-06 00:30:09 +00:00
Steve Naroff
7d317e0593 Add post-build event for clangDriver (to copy clang.exe into "dstroot"). 
llvm-svn: 58783
 2008-11-06 00:11:31 +00:00
Evan Cheng
7390b46342 Undo 58778 but makes the binary dump prettier. 
llvm-svn: 58782
 2008-11-05 23:44:08 +00:00
Bill Wendling
538cbf1e09 Add comments to function. 
llvm-svn: 58781
 2008-11-05 23:42:27 +00:00
Evan Cheng
ce97712aa6 Encode pic load / store instructions; fix some encoding bugs. 
llvm-svn: 58780
 2008-11-05 23:22:34 +00:00
Evan Cheng
c0a36d4aef Add command line option -entry-funcion to override entry function (default is main). 
llvm-svn: 58779
 2008-11-05 23:21:52 +00:00
Evan Cheng
575f3150cf Remove debug output that's not really useful. 
llvm-svn: 58778
 2008-11-05 23:21:11 +00:00
Dan Gohman
aeaf83cfb8 Make ISel ignore dead nodes. The DAGCombiner normally eliminates 
dead nodes, but in this case its missing one. Fixing the DAGCombiner
is desirable, but it's somewhat involved.

llvm-svn: 58777
 2008-11-05 22:56:47 +00:00
Andrew Lenharth
81ebe77943 opt was not exporting the Mangler symbols 
llvm-svn: 58775
 2008-11-05 22:42:50 +00:00
Devang Patel
9600e3e1b2 Add PR number. 
llvm-svn: 58765
 2008-11-05 18:41:15 +00:00
Evan Cheng
9970c31dcf Restructure ARM code emitter to use instruction formats instead of addressing modes to determine how to encode instructions. 
llvm-svn: 58764
 2008-11-05 18:35:52 +00:00
Dan Gohman
022c4b719c Use an assert to check that SelectCode isn't called on 
nodes that are already selected.

llvm-svn: 58763
 2008-11-05 18:30:52 +00:00
Dan Gohman
cd2c7f16c0 The HadDelete field is no longer used. 
llvm-svn: 58761
 2008-11-05 17:35:14 +00:00
Dan Gohman
1db84e57c5 Reintroduce a comment that was removed with the AddToISelQueue 
changes.

llvm-svn: 58760
 2008-11-05 17:16:24 +00:00
Dan Gohman
d308ef44f6 Update some comments to reflect the new code. 
llvm-svn: 58759
 2008-11-05 17:13:57 +00:00
Richard Osborne
efd7edc731 Test commit, add Makefile for XCore target, more to follow. 
llvm-svn: 58755
 2008-11-05 09:53:58 +00:00
Duncan Sands
f56e2fb5c2 Fix thinko in ppcf128 expansion of truncating store. 
llvm-svn: 58753
 2008-11-05 07:17:27 +00:00
Evan Cheng
1378d6c7a9 Add more vector move low and zero-extend patterns. 
llvm-svn: 58752
 2008-11-05 06:04:51 +00:00
Evan Cheng
1bde698192 Type of shuffle mask has changed. 
llvm-svn: 58751
 2008-11-05 06:04:18 +00:00
Evan Cheng
fdd6d65e39 Indentation. 
llvm-svn: 58750
 2008-11-05 06:03:38 +00:00
Dan Gohman
cd4b68bee9 Eliminate the ISel priority queue, which used the topological order for a 
priority function. Instead, just iterate over the AllNodes list, which is
already in topological order. This eliminates a fair amount of bookkeeping,
and speeds up the isel phase by about 15% on many testcases.

The impact on most targets is that AddToISelQueue calls can be simply removed.

In the x86 target, there are two additional notable changes.

The rule-bending AND+SHIFT optimization in MatchAddress that creates new
pre-isel nodes during isel is now a little more verbose, but more robust.
Instead of either creating an invalid DAG or creating an invalid topological
sort, as it has historically done, it can now just insert the new nodes into
the node list at a position where they will be consistent with the topological
ordering.

Also, the address-matching code has logic that checked to see if a node was
"already selected". However, when a node is selected, it has all its uses
taken away via ReplaceAllUsesWith or equivalent, so it won't recieve any
further visits from MatchAddress. This code is now removed.

llvm-svn: 58748
 2008-11-05 04:14:16 +00:00
Dan Gohman
215587186e Use getTargetConstant instead of getConstant for nodes that should not be visited 
by isel and potentially forced into registers.

llvm-svn: 58747
 2008-11-05 02:06:09 +00:00
Evan Cheng
2702e22b83 Rename isGVLazyPtr to isGVNonLazyPtr relocation. This represents Mac OS X 
indirect gv reference. Please don't call it lazy.

llvm-svn: 58746
 2008-11-05 01:50:32 +00:00
Devang Patel
5ca10e5295 New test case. 
llvm-svn: 58745
 2008-11-05 01:40:30 +00:00