Chris Lattner
ba9e3e2fb1
Once we have a way to fold spill code reloads into instructions, we have a way to use it. :)
...
llvm-svn: 11517
2004-02-17 04:08:37 +00:00
Alkis Evlogimenos
4f7c2d9e5e
Fix spilled interval update. It was too conservative.
...
llvm-svn: 11516
2004-02-17 04:04:20 +00:00
Chris Lattner
ddedac59fe
Refactor code a bit. No functionality changes, though the comment hints at things to come.
...
llvm-svn: 11515
2004-02-17 03:57:19 +00:00
Chris Lattner
ecc7d6e27a
Adjust to recent changes
...
llvm-svn: 11514
2004-02-17 03:03:47 +00:00
Chris Lattner
946e46596f
Add two missing pieces from last checkin
...
llvm-svn: 11513
2004-02-17 03:03:36 +00:00
Chris Lattner
c14686440f
Rearrange code to eliminate warnings
...
llvm-svn: 11512
2004-02-17 02:58:36 +00:00
Alkis Evlogimenos
a5ef4a5da7
Add peephole optimizations for ADD [MEM], IMM8 instructions.
...
llvm-svn: 11511
2004-02-16 23:50:18 +00:00
Alkis Evlogimenos
f6ce2e313a
Add two more variants of add. Update comments.
...
llvm-svn: 11510
2004-02-16 23:48:42 +00:00
John Criswell
6d66a493e6
Preemptive additions for the MallocBench tests.
...
llvm-svn: 11507
2004-02-16 23:32:26 +00:00
Chris Lattner
0cb8855a1c
Only spit out warning for functions that take pointers, not for sin and the like
...
Add more special case handling for stdio functions. I feel dirty, how about you?
llvm-svn: 11506
2004-02-16 22:57:19 +00:00
Chris Lattner
04b60fe5ad
Move the folding of gep null, 0, 0, 0 to a place where it can be shared and
...
enjoyed by all, fixing a fixme. Add an assert
llvm-svn: 11505
2004-02-16 20:46:13 +00:00
Misha Brukman
4dd7a7245f
PreSelection isn't optional and so there's no way to turn it off.
...
llvm-svn: 11504
2004-02-16 19:45:26 +00:00
Chris Lattner
cedfcf5bca
memset and bcopy and now unified by the llvm.memset intrinsic
...
llvm-svn: 11503
2004-02-16 18:37:40 +00:00
Chris Lattner
544c9781db
Add some ADD instructions that take memory operands for Alkis
...
llvm-svn: 11502
2004-02-16 18:19:31 +00:00
John Criswell
62c832c68c
Adjusted the default pathname to the SPEC95 benchmarks. The new directory
...
has source code corrections and some input files pre-filtered for use
with the LLVM test suite.
llvm-svn: 11498
2004-02-16 14:55:18 +00:00
Alkis Evlogimenos
14f3fe81c6
Add LeakDetection to MachineInstr.
...
Move out of line member functions of MachineBasicBlock to
MachineBasicBlock.cpp.
llvm-svn: 11497
2004-02-16 07:17:43 +00:00
Chris Lattner
e42732e75f
Implement test/Regression/Transforms/SimplifyCFG/UncondBranchToReturn.ll,
...
see the testcase for the reasoning.
llvm-svn: 11496
2004-02-16 06:35:48 +00:00
Chris Lattner
58d4db3f27
New testcase, details in the comments
...
llvm-svn: 11495
2004-02-16 06:35:19 +00:00
Chris Lattner
4db2d22bea
Fold PHI nodes of constants which are only used by a single cast. This implements
...
phi.ll:test4
llvm-svn: 11494
2004-02-16 05:07:08 +00:00
Chris Lattner
e9613be389
A new testcase for a situation that occurs in 181.mcf
...
llvm-svn: 11493
2004-02-16 05:06:36 +00:00
Chris Lattner
b36d908f7b
Teach LLVM to unravel the "swap idiom". This implements:
...
Regression/Transforms/InstCombine/xor.ll:test20
llvm-svn: 11492
2004-02-16 03:54:20 +00:00
Chris Lattner
98c26a7842
Add a test for the "swap idiom", which LLVM should be able to unravel.
...
llvm-svn: 11491
2004-02-16 03:53:44 +00:00
Chris Lattner
c207635fd5
Implement Transforms/InstCombine/xor.ll:test19
...
llvm-svn: 11490
2004-02-16 01:20:27 +00:00
Chris Lattner
5c063c9348
Test for xor chains
...
llvm-svn: 11489
2004-02-16 01:19:52 +00:00
Chris Lattner
5f25fb0dd7
Fix a bug in the recent rewrite of the leakdetector that caused all of the
...
nightly tests to be really messed up. The problem was that the new leakdetector
was depending on undefined behavior: the order of destruction of static objects.
llvm-svn: 11488
2004-02-15 23:33:48 +00:00
Chris Lattner
aebc66a1ef
Document bug 240
...
llvm-svn: 11487
2004-02-15 23:09:07 +00:00
Chris Lattner
83a0044077
Moving CBE tests to test/Regression/CodeGen/CBackend
...
llvm-svn: 11486
2004-02-15 22:56:30 +00:00
Chris Lattner
5df6d8de9b
When the user runs 'llc foo.bc -march=c', write the output to "foo.cbe.c", not
...
to "foo.s".
llvm-svn: 11485
2004-02-15 22:54:19 +00:00
Chris Lattner
a95bd44282
Now that the lowerinvoke pass inserts calls to llvm.setjmp/llvm.longjmp, some
...
hacks can be banished. Also, this gives us the opportunity to emit special code
for the setjmp/longjmps which alows the elimination of one GCC warning for every
setjmp/longjmp site (which is often THOUSANDS in C++ programs). Yaay!
llvm-svn: 11484
2004-02-15 22:51:47 +00:00
Chris Lattner
303ca1e509
By default, llvm.setjmp/llvm.longjmp intrinsics get lowered to their libc counterparts
...
llvm-svn: 11483
2004-02-15 22:24:51 +00:00
Chris Lattner
d85e061575
Instead of producing calls to setjmp/longjmp, produce uses of the
...
llvm.setjmp/llvm.longjmp intrinsics.
llvm-svn: 11482
2004-02-15 22:24:27 +00:00
Chris Lattner
25530a12a1
Refactor code. Now the intrinsic lowering pass tries to recycle preexisting
...
prototypes, even if they don't precisely match what it would prefer to use.
This fixes: CBackend/2004-02-15-PreexistingExternals.llx compiling it into:
ltmp_0_30 = memcpy(l14_C, 4u, 17);
ltmp_1_30 = memcpy(((int *)l27_A), ((unsigned )(long)l27_B), ((int )123u));
instead of:
ltmp_0_30 = memcpy(l14_C, 4u, 17);
ltmp_1_27 = l43_memcpy(l27_A, l27_B, 123u);
Which does the wrong thing as you could imagine.
llvm-svn: 11481
2004-02-15 22:16:39 +00:00
Chris Lattner
5c49d123ad
New testcase
...
llvm-svn: 11480
2004-02-15 22:14:46 +00:00
Alkis Evlogimenos
e27f33f00e
This pass should not require phi elimination or live variable
...
analysis. It should only preserve them and update LiveVariables if it
already ran.
llvm-svn: 11479
2004-02-15 21:50:32 +00:00
Chris Lattner
a8d97e4e74
Finegrainify namespacification
...
Remove one of the operands of a two operand instruction
llvm-svn: 11478
2004-02-15 21:38:28 +00:00
Alkis Evlogimenos
bbf53937a4
Make dense maps keyed on physical registers smallerusing
...
MRegisterInfo::getNumRegs() instead of
MRegisterInfo::FirstVirtualRegister.
Also use MRegisterInfo::is{Physical,Virtual}Register where
appropriate.
llvm-svn: 11477
2004-02-15 21:37:17 +00:00
Alkis Evlogimenos
2c5ddd20ba
Eliminate the use of spill (reserved) registers.
...
llvm-svn: 11476
2004-02-15 10:24:21 +00:00
Chris Lattner
8579a6fafc
QOI bug fixed
...
llvm-svn: 11475
2004-02-15 06:00:04 +00:00
Chris Lattner
76b2ff4ded
Adjustments to support the new ConstantAggregateZero class
...
llvm-svn: 11474
2004-02-15 05:55:15 +00:00
Chris Lattner
7bea8084e0
Add support for the new ConstantAggregateZero class
...
llvm-svn: 11473
2004-02-15 05:54:27 +00:00
Chris Lattner
834b1272f3
Make the JIT zero out globals with memset instead of an element at a time. This
...
should speed it up a bit on a lot of programs
llvm-svn: 11472
2004-02-15 05:54:06 +00:00
Chris Lattner
218eb798a2
No need to scan zero initializers. This should make DSA a bit faster.
...
llvm-svn: 11471
2004-02-15 05:53:42 +00:00
Chris Lattner
9fba3da879
Add a new ConstantAggregateZero class, to fix PR239. This makes zero
...
initializers for constant structs and arrays take constant space, instead of
space proportinal to the number of elements. This reduces the memory usage of
the LLVM compiler by hundreds of megabytes when compiling some nasty SPEC95
benchmarks.
llvm-svn: 11470
2004-02-15 05:53:04 +00:00
Chris Lattner
2d6fca9717
finegrainify namespacification
...
llvm-svn: 11469
2004-02-15 05:52:36 +00:00
Chris Lattner
e9fbbc25a1
Bug fixed
...
llvm-svn: 11468
2004-02-15 05:47:37 +00:00
Chris Lattner
015e821279
ConstantArray::get and ConstantStruct::get now just return pointers to
...
'Constant', instead of specific subclass pointers. In the future, these will
return an instance of ConstantAggregateZero if all of the inputs are zeros.
llvm-svn: 11467
2004-02-15 04:14:47 +00:00
Chris Lattner
37a716fa80
Remove dependence on return type of ConstantStruct::get
...
llvm-svn: 11466
2004-02-15 04:07:32 +00:00
Chris Lattner
c75bf528c1
Remove dependence on the return type of ConstantArray::get
...
llvm-svn: 11463
2004-02-15 04:05:58 +00:00
Chris Lattner
5d56c478ba
Keep a cache of non-abstract null arrays and structs. This speeds up llvm-dis
...
from 16.57 -> 13.46s on 129.compress.
llvm-svn: 11462
2004-02-15 02:46:46 +00:00
Chris Lattner
0836c10052
Testcase for PR205: [llvmgcc] C front-end does not emit 'zeroinitializer' when possible
...
llvm-svn: 11461
2004-02-15 02:19:08 +00:00