Johnny Chen
bbc71b2904
Add encoding bits for some Thumb instructions. Plus explicitly set the top two
...
bytes of Inst to 0x0000 for the benefit of the Thumb decoder.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91496 91177308-0d34-0410-b5e6-96231b3b80d8
2009-12-16 02:32:54 +00:00
Johnny Chen
d68e119c0f
Added encoding bits for the Thumb ISA. Initial checkin.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91434 91177308-0d34-0410-b5e6-96231b3b80d8
2009-12-15 17:24:14 +00:00
Jim Grosbach
7c03dbd8ed
Add ARMv6 memory and sync barrier instructions
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91329 91177308-0d34-0410-b5e6-96231b3b80d8
2009-12-14 21:24:16 +00:00
Jim Grosbach
a623f5a58d
correct selection requirements for thumb2 vs. arm versions of the barrier intrinsics
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91313 91177308-0d34-0410-b5e6-96231b3b80d8
2009-12-14 19:24:11 +00:00
Jim Grosbach
c219e4dd59
add Thumb2 atomic and memory barrier instruction definitions
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91310 91177308-0d34-0410-b5e6-96231b3b80d8
2009-12-14 18:56:47 +00:00
Anton Korobeynikov
5cdc3a949a
Materialize global addresses via movt/movw pair, this is always better
...
than doing the same via constpool:
1. Load from constpool costs 3 cycles on A9, movt/movw pair - just 2.
2. Load from constpool might stall up to 300 cycles due to cache miss.
3. Movt/movw does not use load/store unit.
4. Less constpool entries => better compiler performance.
This is only enabled on ELF systems, since darwin does not have needed
relocations (yet).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89720 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-24 00:44:37 +00:00
Jim Grosbach
6935efcb66
80 column violations
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89718 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-24 00:20:27 +00:00
Jim Grosbach
15e6ef886d
fold immediate of a + Const into the user as a subtract if it can fit as a negated two-part immediate.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89694 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-23 20:35:53 +00:00
Evan Cheng
4aedb61d03
Remat VLDRD from constpool. Clean up some instruction property specifications.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89478 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-20 19:57:15 +00:00
Evan Cheng
b9803a8fa6
- Add pseudo instructions tLDRpci_pic and t2LDRpci_pic which does a pc-relative
...
load of a GV from constantpool and then add pc. It allows the code sequence to
be rematerializable so it would be hoisted by machine licm.
- Add a late pass to break these pseudo instructions into a number of real
instructions. Also move the code in Thumb2 IT pass that breaks up t2MOVi32imm
to this pass. This is done before post regalloc scheduling to allow the
scheduler to proper schedule these instructions. It also allow them to be
if-converted and shrunk by later passes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@86304 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-06 23:52:48 +00:00
Evan Cheng
5a1cd36019
Fix t2Int_eh_sjlj_setjmp. Immediate form of orr is a 32-bit instruction. So it should be 22 bytes instead of 20 bytes long.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85965 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-03 23:13:34 +00:00
Bob Wilson
907eebd5a6
Put BlockAddresses into ARM constant pools.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85824 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-02 20:59:23 +00:00
David Goodwin
2f54a2fd85
Fix schedule model for BFC.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85809 91177308-0d34-0410-b5e6-96231b3b80d8
2009-11-02 17:28:36 +00:00
Evan Cheng
9eda68988e
It's safe to remat t2LDRpci; Add PseudoSourceValue to load / store's to enable more machine licm. More changes coming.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85643 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-31 03:39:36 +00:00
Bob Wilson
ddb16df912
Add ARM codegen for indirect branches.
...
clang/test/CodeGen/indirect-goto.c runs! (unoptimized)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85577 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-30 05:45:42 +00:00
Dan Gohman
533297b58d
Rename usesCustomDAGSchedInserter to usesCustomInserter, and update a
...
bunch of associated comments, because it doesn't have anything to do
with DAGs or scheduling. This is another step in decoupling MachineInstr
emitting from scheduling.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85517 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-29 18:10:34 +00:00
Evan Cheng
699bebac4f
Change Thumb1 and Thumb2 instructions to separate opcode from operands with a tab instead of a space.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85184 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-27 00:08:59 +00:00
Jim Grosbach
65b7f3af76
Improve handling of immediates by splitting 32-bit immediates into two 16-bit
...
immediate operands when they will fit into the using instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@84778 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-21 20:44:34 +00:00
Evan Cheng
2095659a85
Match more patterns to movt.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@84751 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-21 08:15:52 +00:00
Sandeep Patel
47eedaa8fa
Add ARMv6T2 SBFX/UBFX instructions. Approved by Anton Korobeynikov.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@84009 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-13 18:59:48 +00:00
Evan Cheng
0d92f5f768
Add hasExtraSrcRegAllocReq and hasExtraDefRegAllocReq flags to ld / st multiple,
...
ld / st pairs, etc.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83197 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-01 08:22:27 +00:00
Evan Cheng
d20d658675
Change ld/st multiples to explicitly model the writeback to base register. This fixes most of the -ldstopti-before-sched2 regressions.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83191 91177308-0d34-0410-b5e6-96231b3b80d8
2009-10-01 01:33:39 +00:00
Jim Grosbach
c732adf3a1
Add "isBarrier = 1" to return instructions.
...
Patch by Sylvere Teissier.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83135 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-30 01:35:11 +00:00
Evan Cheng
5adb66a646
Make ARM and Thumb2 32-bit immediate materialization into a single 32-bit pseudo
...
instruction. This makes it re-materializable.
Thumb2 will split it back out into two instructions so IT pass will generate the
right mask. Also, this expose opportunies to optimize the movw to a 16-bit move.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82982 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-28 09:14:39 +00:00
Anton Korobeynikov
6a2fa325c1
Use movt/movw pair to materialize 32 bit constants on ARMv6T2+.
...
This should be better than single load from constpool.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82948 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-27 23:52:58 +00:00
Evan Cheng
e298ab26b1
Enable pre-regalloc load / store multiple pass for Thumb2.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82893 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-27 09:46:04 +00:00
David Goodwin
ca01a8d4ab
RRX reads CPSR.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@80699 91177308-0d34-0410-b5e6-96231b3b80d8
2009-09-01 18:32:09 +00:00
Evan Cheng
d17479e845
Print a nl before pic labels so they start at a new line. This makes assembly more readable.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@80350 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-28 06:59:37 +00:00
Bob Wilson
4f38b383d5
Rename ARM "lane_cst" operands to "nohash_imm" since they are used for
...
several things other than Neon vector lane numbers. For inline assembly
operands with a "c" print code, check that they really are immediates.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79676 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-21 21:58:55 +00:00
David Goodwin
5d598aaf3d
Update Cortex-A8 instruction itineraries for integer instructions.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79436 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-19 18:00:44 +00:00
Evan Cheng
51f39961c3
Fix revsh pattern.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79318 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-18 05:43:23 +00:00
Evan Cheng
a1efbbdbf3
Shrink ADR and LDR from constantpool late during constantpool island pass.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78970 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-14 00:32:16 +00:00
Jim Grosbach
f35d21617e
Add missing defs of R2 and D1.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78918 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-13 16:59:44 +00:00
David Goodwin
6d3d9c3fc3
Finalize itineraries for cortex-a8 integer multiply
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78908 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-13 15:51:13 +00:00
Jim Grosbach
8db5cce021
Remove unnecessary newline
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78905 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-13 15:12:16 +00:00
Jim Grosbach
1add659b0a
Correct comment wording
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78904 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-13 15:11:43 +00:00
David Goodwin
1a8f36e3ce
Enhance the InstrStage object to enable the specification of an Itinerary with overlapping stages. The default is to maintain the current behavior that the "next" stage immediately follows the previous one.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78827 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-12 18:31:53 +00:00
Jim Grosbach
378756c0f2
register naming cleanup (s/ip/r12/)
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78806 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-12 15:21:13 +00:00
Evan Cheng
ea253b99e9
Remove an Darwin assembler workaround.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78777 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-12 01:56:42 +00:00
Evan Cheng
4b322e58b7
Shrinkify Thumb2 load / store multiple instructions.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78717 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-11 21:11:32 +00:00
Owen Anderson
825b72b057
Split EVT into MVT and EVT, the former representing _just_ a primitive type, while
...
the latter is capable of representing either a primitive or an extended type.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78713 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-11 20:47:22 +00:00
Jim Grosbach
5aa1684e5d
Add Thumb2 eh_sjlj_setjmp implementation
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78701 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-11 19:42:21 +00:00
Evan Cheng
1cf5783dd7
80 column violation.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78657 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-11 08:47:46 +00:00
Owen Anderson
e50ed30282
Rename MVT to EVT, in preparation for splitting SimpleValueType out into its own struct type.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78610 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-10 22:56:29 +00:00
Evan Cheng
e8af1f9afe
Add support to reduce most of 32-bit Thumb2 arithmetic instructions.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78550 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-10 02:37:24 +00:00
Anton Korobeynikov
8e9ece75db
Use subclassing to print lane-like immediates (w/o hash) eliminating
...
'no_hash' modifier. Hopefully this will make Daniel happy :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78514 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-08 23:10:41 +00:00
Evan Cheng
d77c7aba83
Thumb2 32-bit ldm / stm needs .w suffix if submode is ia.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78410 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-07 21:19:10 +00:00
Evan Cheng
861986401e
It turns out most of the thumb2 instructions are not allowed to touch SP. The semantics of such instructions are unpredictable. We have just been lucky that tests have been passing.
...
This patch takes pain to ensure all the PEI lowering code does the right thing when lowering frame indices, insert code to manipulate stack pointers, etc. It's also custom lowering dynamic stack alloc into pseudo instructions so we can insert the right instructions at scheduling time.
This fixes PR4659 and PR4682.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78361 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-07 00:34:42 +00:00
David Goodwin
8b7d7ade85
Add parameter to pattern classes to enable an itinerary to be specified for instructions. For now just use the existing itineraries or NoItinerary.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78321 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-06 16:52:47 +00:00
Evan Cheng
35d6c41fde
Fix part 1 of pr4682. PICADD is a 16-bit instruction even in thumb2 mode.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78126 91177308-0d34-0410-b5e6-96231b3b80d8
2009-08-04 23:47:55 +00:00