| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
| |
PEI can't handle the pseudo-instructions. This can be removed when the
pseudo-instructions are replaced by normal predicated instructions.
Fixes PR13628.
llvm-svn: 162130
|
| |
|
|
| |
llvm-svn: 162094
|
| |
|
|
|
|
|
|
|
|
| |
It is not my plan to duplicate the entire ARM instruction set with
predicated versions. We need a way of representing predicated
instructions in SSA form without requiring a separate opcode.
Then the pseudo-instructions can go away.
llvm-svn: 162061
|
| |
|
|
|
|
| |
Use the target independent select analysis hooks.
llvm-svn: 162060
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
The ARM select instructions are just predicated moves. If the select is
the only use of an operand, the instruction defining the operand can be
predicated instead, saving one instruction and decreasing register
pressure.
This implementation can turn AND/ORR/EOR instructions into their
corresponding ANDCC/ORRCC/EORCC variants. Ideally, we should be able to
predicate any instruction, but we don't yet support predicated
instructions in SSA form.
llvm-svn: 161994
|
| |
|
|
|
|
|
|
|
| |
stuff
(this corresponds by spilling/reloading regs in DTriple / DQuad reg classes).
No testcase, found by inspection.
llvm-svn: 161300
|
| |
|
|
|
|
|
|
| |
classes, which
were missed for no reason. This fixes PR13377
llvm-svn: 161299
|
| |
|
|
| |
llvm-svn: 160621
|
| |
|
|
| |
llvm-svn: 160093
|
| |
|
|
|
|
|
|
| |
It is safe if CPSR is killed or re-defined.
When we are done with the basic block, check whether CPSR is live-out.
Do not optimize away cmp if CPSR is live-out.
llvm-svn: 160090
|
| |
|
|
|
|
| |
My last checkin was apparently not the branch I intended. It was missing one change (added by chandlerc), and contained a spurious change.
llvm-svn: 159548
|
| |
|
|
|
|
| |
Reapplies r159406 with minor cleanup. The regressions appear to have been spurious.
llvm-svn: 159541
|
| |
|
|
|
|
|
|
| |
Use getUniqueVRegDef.
Replace a loop with existing interfaces: modifiesRegister and readsRegister.
Factor out code into inline functions and simplify the code.
llvm-svn: 159470
|
| |
|
|
|
|
| |
instructions with two register operands.
llvm-svn: 159465
|
| |
|
|
|
|
| |
This reverts commit r159406. I noticed a performance regression so I'll back out for now.
llvm-svn: 159411
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
The TargetInstrInfo::getNumMicroOps API does not change, but soon it
will be used by MachineScheduler. Now each subtarget can specify the
number of micro-ops per itinerary class. For ARM, this is currently
always dynamic (-1), because it is used for load/store multiple which
depends on the number of register operands.
Zero is now a valid number of micro-ops. This can be used for
nop pseudo-instructions or instructions that the hardware can squash
during dispatch.
llvm-svn: 159406
|
| |
|
|
|
|
| |
possible. Sorry. rdar://11745134
llvm-svn: 159236
|
| |
|
|
|
|
|
|
|
|
| |
More condition codes are included when deciding whether to remove cmp after
a sub instruction. Specifically, we extend from GE|LT|GT|LE to
GE|LT|GT|LE|HS|LS|HI|LO|EQ|NE. If we have "sub a, b; cmp b, a; movhs", we
should be able to replace with "sub a, b; movls".
rdar: 11725965
llvm-svn: 159166
|
| |
|
|
|
|
|
|
|
|
| |
This is a minor drive-by fix with no robust way to unit test.
As an example see neon-div.ll:
SU(16): %Q8<def> = VMOVLsv4i32 %D17, pred:14, pred:%noreg, %Q8<imp-use,kill>
val SU(1): Latency=2 Reg=%Q8
...should be latency=1
llvm-svn: 158960
|
| |
|
|
|
|
|
|
| |
Minor drive by fix to cleanup latency computation. Calling
getOperandLatency with a deliberately incorrect operand index does not
give you the latency you want.
llvm-svn: 158959
|
| |
|
|
| |
llvm-svn: 158164
|
| |
|
|
|
|
| |
Match expectations of the new latency API. Cleanup and make the logic consistent.
llvm-svn: 158163
|
| |
|
|
| |
llvm-svn: 158162
|
| |
|
|
| |
llvm-svn: 158161
|
| |
|
|
|
|
|
| |
Minimum latency determines per-cycle scheduling groups.
Expected latency determines critical path and cost.
llvm-svn: 158021
|
| |
|
|
|
|
| |
uint16_t. Simplify loop iterating over one of those tables. No functional change intended.
llvm-svn: 157367
|
| |
|
|
|
|
| |
Found by GCC's maybe-uninitialized.
llvm-svn: 156780
|
| |
|
|
| |
llvm-svn: 156620
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch will optimize the following cases:
sub r1, r3 | sub r1, imm
cmp r3, r1 or cmp r1, r3 | cmp r1, imm
bge L1
TO
subs r1, r3
bge L1 or ble L1
If the branch instruction can use flag from "sub", then we can replace
"sub" with "subs" and eliminate the "cmp" instruction.
rdar: 10734411
llvm-svn: 156599
|
| |
|
|
|
|
| |
This commit broke an external linux bot and gave a compile-time warning.
llvm-svn: 156556
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch will optimize the following cases:
sub r1, r3 | sub r1, imm
cmp r3, r1 or cmp r1, r3 | cmp r1, imm
bge L1
TO
subs r1, r3
bge L1 or ble L1
If the branch instruction can use flag from "sub", then we can replace
"sub" with "subs" and eliminate the "cmp" instruction.
rdar: 10734411
llvm-svn: 156550
|
| |
|
|
|
|
|
|
|
|
| |
A MOVCCr instruction can be commuted by inverting the condition. This
can help reduce register pressure and remove unnecessary copies in some
cases.
<rdar://problem/11182914>
llvm-svn: 154033
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
ARM recently gained DPair, DTriple, and DQuad register classes.
Update copyPhysReg() to handle copies in these register classes.
No test case, it is difficult to make the register allocator emit the
odd copies reliably. The missing DPair copy caused a failure on
partialsums in the nightly test suite.
<rdar://problem/11147997>
llvm-svn: 153686
|
| |
|
|
|
|
|
|
|
| |
The arm_neon intrinsics can create virtual registers from the DPair
register class which allows both even-odd and odd-even D-register pairs.
This fixes PR12389.
llvm-svn: 153603
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
produces a 32-bit immediate which is consumed by the use. It tries to
fold the immediate by breaking it into two parts and fold them into the
immmediate fields of two uses. e.g
movw r2, #40885
movt r3, #46540
add r0, r0, r3
=>
add.w r0, r0, #3019898880
add.w r0, r0, #30146560
;
However, this transformation is incorrect if the user produces a flag. e.g.
movw r2, #40885
movt r3, #46540
adds r0, r0, r3
=>
add.w r0, r0, #3019898880
adds.w r0, r0, #30146560
Note the adds.w may not set the carry flag even if the original sequence
would.
rdar://11116189
llvm-svn: 153484
|
| |
|
|
| |
llvm-svn: 153422
|
| |
|
|
|
|
|
| |
Register pair VLD1/VLD2 all-lanes instructions. Kill off more of the
pseudos as a result.
llvm-svn: 152150
|
| |
|
|
|
|
|
|
|
|
| |
When an instruction only writes sub-registers, it is still necessary to
add an <imp-def> operand for the super-register. When reloading into a
virtual register, rewriting will add the operand, but when loading
directly into a virtual register, the <imp-def> operand is still
necessary.
llvm-svn: 152095
|
| |
|
|
|
|
|
|
|
| |
With the new composite physical registers to represent arbitrary pairs
of DPR registers, we don't need the pseudo-registers anymore. Get rid of
a bunch of them that use DPR register pairs and just use the real
instructions directly instead.
llvm-svn: 152045
|
| |
|
|
|
|
|
|
|
|
|
| |
MachineOperands that define part of a virtual register must have an
<undef> flag if they are not intended as read-modify-write operands.
The old trick of adding an <imp-def> operand doesn't work any longer.
Fixes PR12177.
llvm-svn: 152008
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Without this hook, functions w/ a completely empty body (including no
epilogue) will cause an MCEmitter assertion failure.
For example,
define internal fastcc void @empty_function() {
unreachable
}
rdar://10947471
llvm-svn: 151673
|
| |
|
|
| |
llvm-svn: 151113
|
| |
|
|
|
|
|
| |
Even if a call instruction has %SP<imp-def> operands, it doesn't change
the value of the stack pointer.
llvm-svn: 151104
|
| |
|
|
|
|
| |
MSP430, PPC, PTX, Sparc, X86, XCore.
llvm-svn: 150878
|
| |
|
|
| |
llvm-svn: 150833
|
| |
|
|
|
|
| |
Calls always clobber CPSR.
llvm-svn: 150831
|
| |
|
|
| |
llvm-svn: 149961
|
| |
|
|
| |
llvm-svn: 149846
|
| |
|
|
| |
llvm-svn: 148578
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Now that canRealignStack() understands frozen reserved registers, it is
safe to use it for aligned spill instructions.
It will only return true if the registers reserved at the beginning of
register allocation allow for dynamic stack realignment.
<rdar://problem/10625436>
llvm-svn: 147579
|