Commit Graph

10416 Commits

Author SHA1 Message Date
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