sink them into MC layer.
- Added MCInstrInfo, which captures the tablegen generated static data. Chang
TargetInstrInfo so it's based off MCInstrInfo.
llvm-svn: 134021
all LDR/STR changes and left them to a future patch. Passing all
checks now.
- Implement asm parsing support for LDRT, LDRBT, STRT, STRBT and
fix the encoding wherever is possible.
- Add a new encoding bit to describe the index mode used and teach
printAddrMode2Operand to check by the addressing mode which index
mode to print.
- Testcases
llvm-svn: 128689
- Implement asm parsing support for LDRT, LDRBT, STRT, STRBT and
{STR,LDC}{2}_{PRE,POST} fixing the encoding wherever is possible.
- Move all instructions which use am2offset without a pattern to use
addrmode2.
- Add a new encoding bit to describe the index mode used and teach
printAddrMode2Operand to check by the addressing mode which index
mode to print.
- Testcases
llvm-svn: 128632
{STR,LDC}{2}_PRE.
- Fixed the encoding in some places.
- Some of those instructions were using am2offset and now use addrmode2.
Codegen isn't affected, instructions which use SelectAddrMode2Offset were not
touched.
- Teach printAddrMode2Operand to check by the addressing mode which index
mode to print.
- This is a work in progress, more work to come. The idea is to change places
which use am2offset to use addrmode2 instead, as to unify assembly parser.
- Add testcases for assembly parser
llvm-svn: 128585
TargetInstrInfo:
Change produceSameValue() to take MachineRegisterInfo as an optional argument.
When in SSA form, targets can use it to make more aggressive equality analysis.
Machine LICM:
1. Eliminate isLoadFromConstantMemory, use MI.isInvariantLoad instead.
2. Fix a bug which prevent CSE of instructions which are not re-materializable.
3. Use improved form of produceSameValue.
ARM:
1. Teach ARM produceSameValue to look pass some PIC labels.
2. Look for operands from different loads of different constant pool entries
which have same values.
3. Re-implement PIC GA materialization using movw + movt. Combine the pair with
a "add pc" or "ldr [pc]" to form pseudo instructions. This makes it possible
to re-materialize the instruction, allow machine LICM to hoist the set of
instructions out of the loop and make it possible to CSE them. It's a bit
hacky, but it significantly improve code quality.
4. Some minor bug fixes as well.
With the fixes, using movw + movt to materialize GAs significantly outperform the
load from constantpool method. 186.crafty and 255.vortex improved > 20%, 254.gap
and 176.gcc ~10%.
llvm-svn: 123905
DAG scheduling during isel. Most new functionality is currently
guarded by -enable-sched-cycles and -enable-sched-hazard.
Added InstrItineraryData::IssueWidth field, currently derived from
ARM itineraries, but could be initialized differently on other targets.
Added ScheduleHazardRecognizer::MaxLookAhead to indicate whether it is
active, and if so how many cycles of state it holds.
Added SchedulingPriorityQueue::HasReadyFilter to allowing gating entry
into the scheduler's available queue.
ScoreboardHazardRecognizer now accesses the ScheduleDAG in order to
get information about it's SUnits, provides RecedeCycle for bottom-up
scheduling, correctly computes scoreboard depth, tracks IssueCount, and
considers potential stall cycles when checking for hazards.
ScheduleDAGRRList now models machine cycles and hazards (under
flags). It tracks MinAvailableCycle, drives the hazard recognizer and
priority queue's ready filter, manages a new PendingQueue, properly
accounts for stall cycles, etc.
llvm-svn: 122541
difficult on current ARM implementations for a few reasons.
1. Even though a single vmla has latency that is one cycle shorter than a pair
of vmul + vadd, a RAW hazard during the first (4? on Cortex-a8) can cause
additional pipeline stall. So it's frequently better to single codegen
vmul + vadd.
2. A vmla folowed by a vmul, vmadd, or vsub causes the second fp instruction to
stall for 4 cycles. We need to schedule them apart.
3. A vmla followed vmla is a special case. Obvious issuing back to back RAW
vmla + vmla is very bad. But this isn't ideal either:
vmul
vadd
vmla
Instead, we want to expand the second vmla:
vmla
vmul
vadd
Even with the 4 cycle vmul stall, the second sequence is still 2 cycles
faster.
Up to now, isel simply avoid codegen'ing fp vmla / vmls. This works well enough
but it isn't the optimial solution. This patch attempts to make it possible to
use vmla / vmls in cases where it is profitable.
A. Add missing isel predicates which cause vmla to be codegen'ed.
B. Make sure the fmul in (fadd (fmul)) has a single use. We don't want to
compute a fmul and a fmla.
C. Add additional isel checks for vmla, avoid cases where vmla is feeding into
fp instructions (except for the #3 exceptional case).
D. Add ARM hazard recognizer to model the vmla / vmls hazards.
E. Add a special pre-regalloc case to expand vmla / vmls when it's likely the
vmla / vmls will trigger one of the special hazards.
Work in progress, only A+B are enabled.
llvm-svn: 120960
Remove movePastCSLoadStoreOps and associated code for simple pointer
increments. Update routines that depended upon other opcodes for save/restore.
Adjust all testcases accordingly.
llvm-svn: 119725
and xor. The 32-bit move immediates can be hoisted out of loops by machine
LICM but the isel hacks were preventing them.
Instead, let peephole optimization pass recognize registers that are defined by
immediates and the ARM target hook will fold the immediates in.
Other changes include 1) do not fold and / xor into cmp to isel TST / TEQ
instructions if there are multiple uses. This happens when the 'and' is live
out, machine sink would have sinked the computation and that ends up pessimizing
code. The peephole pass would recognize situations where the 'and' can be
toggled to define CPSR and eliminate the comparison anyway.
2) Move peephole pass to after machine LICM, sink, and CSE to avoid blocking
important optimizations.
rdar://8663787, rdar://8241368
llvm-svn: 119548
1. Fix pre-ra scheduler so it doesn't try to push instructions above calls to
"optimize for latency". Call instructions don't have the right latency and
this is more likely to use introduce spills.
2. Fix if-converter cost function. For ARM, it should use instruction latencies,
not # of micro-ops since multi-latency instructions is completely executed
even when the predicate is false. Also, some instruction will be "slower"
when they are predicated due to the register def becoming implicit input.
rdar://8598427
llvm-svn: 118135
explicit about the operands. Split out the different variants into separate
instructions. This gives us the ability to, among other things, assign
different scheduling itineraries to the variants. rdar://8477752.
llvm-svn: 117409
"long latency" enough to hoist even if it may increase spilling. Reloading
a value from spill slot is often cheaper than performing an expensive
computation in the loop. For X86, that means machine LICM will hoist
SQRT, DIV, etc. ARM will be somewhat aggressive with VFP and NEON
instructions.
- Enable register pressure aware machine LICM by default.
llvm-svn: 116781
allow target to correctly compute latency for cases where static scheduling
itineraries isn't sufficient. e.g. variable_ops instructions such as
ARM::ldm.
This also allows target without scheduling itineraries to compute operand
latencies. e.g. X86 can return (approximated) latencies for high latency
instructions such as division.
- Compute operand latencies for those defined by load multiple instructions,
e.g. ldm and those used by store multiple instructions, e.g. stm.
llvm-svn: 115755
stick with a constant estimate of 90% (branch predictors are good!), but we might find that we want to provide
more nuanced estimates in the future.
llvm-svn: 115364
Rather than having arbitrary cutoffs, actually try to cost model the conversion.
For now, the constants are tuned to more or less match our existing behavior, but these will be
changed to reflect realistic values as this work proceeds.
llvm-svn: 114973
into OptimizeCompareInstr.
This necessitates the passing of CmpValue around,
so widen the virtual functions to accomodate.
No functionality changes.
llvm-svn: 114428
iterator when an optimization took place. This allows us to do more insane
things with the code than just remove an instruction or two.
llvm-svn: 113640
take multiple cycles to decode.
For the current if-converter clients (actually only ARM), the instructions that
are predicated on false are not nops. They would still take machine cycles to
decode. Micro-coded instructions such as LDM / STM can potentially take multiple
cycles to decode. If-converter should take treat them as non-micro-coded
simple instructions.
llvm-svn: 113570
instruction in the class would be decoded to. Or zero if the number of
uOPs must be determined dynamically.
This will be used to determine the cost-effectiveness of predicating a
micro-coded instruction.
llvm-svn: 113513
(I discovered 2 more copies of the ARM instruction format list, bringing the
total to 4!! Two of them were already out of sync. I haven't yet gotten into
the disassembler enough to know the best way to fix this, but something needs
to be done.) Add support for encoding these instructions.
llvm-svn: 110754
relatively expensive comparison analyzer on each instruction. Also rename the
comparison analyzer method to something more in line with what it actually does.
This pass is will eventually be folded into the Machine CSE pass.
llvm-svn: 110539
This pass tries to remove comparison instructions when possible. For instance,
if you have this code:
sub r1, 1
cmp r1, 0
bz L1
and "sub" either sets the same flag as the "cmp" instruction or could be
converted to set the same flag, then we can eliminate the "cmp" instruction all
together. This is a important for ARM where the ALU instructions could set the
CPSR flag, but need a special suffix ('s') to do so.
llvm-svn: 110423
ARM/PPC/MSP430-specific code (which are the only targets that
implement the hook) can directly reference their target-specific
instrinfo classes.
llvm-svn: 109171
The only folding these load/store architectures can do is converting COPY into a
load or store, and the target independent part of foldMemoryOperand already
knows how to do that.
llvm-svn: 108099
void t(int *cp0, int *cp1, int *dp, int fmd) {
int c0, c1, d0, d1, d2, d3;
c0 = (*cp0++ & 0xffff) | ((*cp1++ << 16) & 0xffff0000);
c1 = (*cp0++ & 0xffff) | ((*cp1++ << 16) & 0xffff0000);
/* ... */
}
It code gens into something pretty bad. But with this change (analogous to the
X86 back-end), it will use ldm and generate few instructions.
llvm-svn: 106693
- This fixed a number of bugs in if-converter, tail merging, and post-allocation
scheduler. If-converter now runs branch folding / tail merging first to
maximize if-conversion opportunities.
- Also changed the t2IT instruction slightly. It now defines the ITSTATE
register which is read by instructions in the IT block.
- Added Thumb2 specific hazard recognizer to ensure the scheduler doesn't
change the instruction ordering in the IT block (since IT mask has been
finalized). It also ensures no other instructions can be scheduled between
instructions in the IT block.
This is not yet enabled.
llvm-svn: 106344
addresses a longstanding deficiency noted in many FIXMEs scattered
across all the targets.
This effectively moves the problem up one level, replacing eleven
FIXMEs in the targets with eight FIXMEs in CodeGen, plus one path
through FastISel where we actually supply a DebugLoc, fixing Radar
7421831.
llvm-svn: 106243
the machine instruction representation of the immediate value to be encoded
into an integer with similar fields as the actual VMOV instruction. This makes
things easier for the disassembler, since it can just stuff the bits into the
immediate operand, but harder for the asm printer since it has to decode the
value to be printed. Testcase for the encoding will follow later when MC has
more support for ARM.
llvm-svn: 105836
instruction defines subregisters.
Any existing subreg indices on the original instruction are preserved or
composed with the new subreg index.
Also substitute multiple operands mentioning the original register by using the
new MachineInstr::substituteRegister() function. This is necessary because there
will soon be <imp-def> operands added to non read-modify-write partial
definitions. This instruction:
%reg1234:foo = FLAP %reg1234<imp-def>
will reMaterialize(%reg3333, bar) like this:
%reg3333:bar-foo = FLAP %reg333:bar<imp-def>
Finally, replace the TargetRegisterInfo pointer argument with a reference to
indicate that it cannot be NULL.
llvm-svn: 105358
- Eliminate TargetInstrInfo::isIdentical and replace it with produceSameValue. In the default case, produceSameValue just checks whether two machine instructions are identical (except for virtual register defs). But targets may override it to check for unusual cases (e.g. ARM pic loads from constant pools).
llvm-svn: 97628
for all the processors where I have tried it, and even when it might not help
performance, the cost is quite low. The opportunities for duplicating
indirect branches are limited by other factors so code size does not change
much due to tail duplicating indirect branches aggressively.
llvm-svn: 90144
Make tail duplication of indirect branches much more aggressive (for targets
that indicate that it is profitable), based on further experience with
this transformation. I compiled 3 large applications with and without
this more aggressive tail duplication and measured minimal changes in code
size. ("size" on Darwin seems to round the text size up to the nearest
page boundary, so I can only say that any code size increase was less than
one 4k page.) Radar 7421267.
llvm-svn: 89814
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).
llvm-svn: 89720
contents of the block to be duplicated. Use this for ARM Cortex A8/9 to
be more aggressive tail duplicating indirect branches, since it makes it
much more likely that they will be predicted in the branch target buffer.
Testcase coming soon.
llvm-svn: 89187
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.
llvm-svn: 86304
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.
llvm-svn: 82982
the only real caller (GetFunctionSizeInBytes) uses it.
The custom ARM implementation of this is basically reimplementing
an assembler poorly for negligible gain. It should be removed
IMNSHO, but I'll leave that to ARMish folks to decide.
llvm-svn: 77877
- This change also makes it possible to switch between ARM / Thumb on a
per-function basis.
- Fixed thumb2 routine which expand reg + arbitrary immediate. It was using
using ARM so_imm logic.
- Use movw and movt to do reg + imm when profitable.
- Other code clean ups and minor optimizations.
llvm-svn: 77300