Commit Graph

10644 Commits

Author SHA1 Message Date
Alkis Evlogimenos
89b0214b76 Add memory operand folding for CMP{rm,mr,mi}{8,16,32}, INCm{8,16,32}
and DECm{8,16,32} instructions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11545 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:49:20 +00:00
Alkis Evlogimenos
509d6d65b5 Add CMP{rm,mr,mi}{8,16,32}, INCm{8,16,32} and DECm{8,16,32} instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11544 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:49:00 +00:00
Alkis Evlogimenos
503770cfc3 Add SUB{rm,mr,mi}{8,16,32} instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11543 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:17:40 +00:00
Chris Lattner
11390e76e7 Add support to the local allocator for fusing spill code into the instructions
that need them.  This is very useful on CISCy targets like the X86 because it
reduces the total spill pressure, and makes better use of it's (large)
instruction set.  Though the X86 backend doesn't know how to rewrite many
instructions yet, this already makes a substantial difference on 176.gcc for
example:

Before:
Time:
   8.0099 ( 31.2%)   0.0100 ( 12.5%)   8.0199 ( 31.2%)   7.7186 ( 30.0%)  Local Register Allocator

Code quality:
734559 asm-printer           - Number of machine instrs printed
111395 ra-local              - Number of registers reloaded
 79902 ra-local              - Number of registers spilled
231554 x86-peephole          - Number of peephole optimization performed

After:
Time:
   7.8700 ( 30.6%)   0.0099 ( 19.9%)   7.8800 ( 30.6%)   7.7892 ( 30.2%)  Local Register Allocator
Code quality:
733083 asm-printer           - Number of machine instrs printed
  2379 ra-local              - Number of reloads fused into instructions
109046 ra-local              - Number of registers reloaded
 79881 ra-local              - Number of registers spilled
230658 x86-peephole          - Number of peephole optimization performed

So by fusing 2300 instructions, we reduced the  static number of instructions
by 1500, and reduces the number of peepholes (and thus the work) by about 900.
This also clearly reduces the number of reload/spill instructions that are
emitted.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11542 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:09:40 +00:00
Alkis Evlogimenos
18bd7bb4d4 Add support for folding memory operands for ADC, SBB and SUB instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11541 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:08:51 +00:00
Alkis Evlogimenos
69da6dba79 Add support for ADC{rm.mr}32 and SBB{rm,mr}32.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11540 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:06:31 +00:00
Chris Lattner
ee0919bb10 Add a (hidden) option to print instructions that fail to fuse. It's looking
like compares and test's would be the next huge win...


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11539 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 08:03:47 +00:00
Alkis Evlogimenos
17dc674c13 Add support for folding memory operands in MOVri{8,16,32} instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11538 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 07:47:20 +00:00
Chris Lattner
5b67252620 Expand the repertoire of the forms we can print and encode.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11537 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 07:40:44 +00:00
Chris Lattner
651fd55d5f Disable this peephole for now. We can't keep track of the fact that the immediate is 8 bits,
but the memory reference is full sized.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11536 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 07:36:32 +00:00
Chris Lattner
cdee28724e Fix a bug in my previous refactoring change... arg!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11535 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 07:02:17 +00:00
Chris Lattner
c4601bf2f3 The CBE is now in llc, not llvm-dis
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11534 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:40:51 +00:00
Chris Lattner
9915cd9e9f The C backend is no longer in llvm-dis, it's in llc
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11533 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:40:06 +00:00
Chris Lattner
df2cf418a8 The CBE is no longer in llvm-dis
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11532 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:39:48 +00:00
Chris Lattner
a7660be6c2 Add an option to disable spill fusing in the X86 backend
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11531 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:30:34 +00:00
Chris Lattner
e87331d11d Fix the mneumonics for the mov instructions to have the source and destination
order in the correct sense!! Arg!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11530 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:28:19 +00:00
Chris Lattner
7ddc3fbd22 Fix the last crimes against nature that used the 'ir' ordering to use the
'ri' ordering instead... no it's not possible to store a register into an
immediate!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11529 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:24:02 +00:00
Chris Lattner
f120ebbf8a GRRR. Move instructions have swapped the order of the r/m operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11528 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:20:20 +00:00
Chris Lattner
6e173a0d9c Rename MOVi[mr] instructions to MOV[rm]i
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11527 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:16:44 +00:00
Chris Lattner
90c38c8141 Whoops, got my cases swapped.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11526 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 06:02:15 +00:00
Chris Lattner
5a051f65d3 Change to match the newer, simpler, interface
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11525 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 05:54:57 +00:00
Chris Lattner
8026a6982e Simplify and document the new interface
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11524 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 05:54:26 +00:00
Chris Lattner
0f9c491abc Add support for folding memory operands into AND and IMUL's
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11523 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 05:46:06 +00:00
Chris Lattner
7c035b73a4 Scrunchify code, by adding helpers. No functionality changes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11522 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 05:35:13 +00:00
Chris Lattner
4ff7876c64 Add mem forms of AND instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11521 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 05:25:50 +00:00
Alkis Evlogimenos
7093d37304 Add LiveIntervals::Interval::empty() member function.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11520 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 05:14:37 +00:00
Alkis Evlogimenos
b499866c05 Add API to check and fold memory operands into instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11519 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 04:33:18 +00:00
Chris Lattner
55b5481255 Rename the IMULri* instructions to IMULrri, as they are actually three address
instructions.  Add forms of these instructions that read from memory


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11518 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 04:26:43 +00:00
Chris Lattner
1e3812c1c5 Once we have a way to fold spill code reloads into instructions, we have a way to use it. :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11517 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 04:08:37 +00:00
Alkis Evlogimenos
355a724bd8 Fix spilled interval update. It was too conservative.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11516 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 04:04:20 +00:00
Chris Lattner
42e0a8fded Refactor code a bit. No functionality changes, though the comment hints at things to come.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11515 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 03:57:19 +00:00
Chris Lattner
ac89164fa2 Adjust to recent changes
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11514 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 03:03:47 +00:00
Chris Lattner
fcdb2c2a7f Add two missing pieces from last checkin
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11513 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 03:03:36 +00:00
Chris Lattner
3e3bcbd222 Rearrange code to eliminate warnings
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11512 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-17 02:58:36 +00:00
Alkis Evlogimenos
31bbb5190b Add peephole optimizations for ADD [MEM], IMM8 instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11511 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 23:50:18 +00:00
Alkis Evlogimenos
7271e0e107 Add two more variants of add. Update comments.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11510 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 23:48:42 +00:00
John Criswell
7727087394 Preemptive additions for the MallocBench tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11507 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 23:32:26 +00:00
Chris Lattner
304e143b16 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?


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11506 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 22:57:19 +00:00
Chris Lattner
2e9bb1a88e 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


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11505 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 20:46:13 +00:00
Misha Brukman
2ca265299c PreSelection isn't optional and so there's no way to turn it off.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11504 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 19:45:26 +00:00
Chris Lattner
eee33b2691 memset and bcopy and now unified by the llvm.memset intrinsic
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11503 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 18:37:40 +00:00
Chris Lattner
e0f636a068 Add some ADD instructions that take memory operands for Alkis
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11502 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 18:19:31 +00:00
John Criswell
542af5f4fb 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.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11498 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 14:55:18 +00:00
Alkis Evlogimenos
aad5c05051 Add LeakDetection to MachineInstr.
Move out of line member functions of MachineBasicBlock to
MachineBasicBlock.cpp.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11497 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 07:17:43 +00:00
Chris Lattner
19831ec853 Implement test/Regression/Transforms/SimplifyCFG/UncondBranchToReturn.ll,
see the testcase for the reasoning.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11496 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 06:35:48 +00:00
Chris Lattner
5ea27d820a New testcase, details in the comments
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11495 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 06:35:19 +00:00
Chris Lattner
7059f2e76b Fold PHI nodes of constants which are only used by a single cast. This implements
phi.ll:test4


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11494 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 05:07:08 +00:00
Chris Lattner
d8bed768ab A new testcase for a situation that occurs in 181.mcf
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11493 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 05:06:36 +00:00
Chris Lattner
26ca7e145e Teach LLVM to unravel the "swap idiom". This implements:
Regression/Transforms/InstCombine/xor.ll:test20


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11492 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 03:54:20 +00:00
Chris Lattner
72695f7bb7 Add a test for the "swap idiom", which LLVM should be able to unravel.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@11491 91177308-0d34-0410-b5e6-96231b3b80d8
2004-02-16 03:53:44 +00:00