This showed up the first time rend() was called on a bundled instruction
in the Mips backend.
Also avoid dereferencing end() in bundle_iterator::operator++().
We still don't have a place to put unit tests for this stuff.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158310 91177308-0d34-0410-b5e6-96231b3b80d8
We turned off the CMN instruction because it had semantics which we weren't
getting correct. If we are comparing with an immediate, then it's okay to use
the CMN instruction.
<rdar://problem/7569620>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158302 91177308-0d34-0410-b5e6-96231b3b80d8
This saves a cast, and zext is more expensive on platforms with subreg support
than trunc is. This occurs in the BSD implementation of memchr(3), see PR12750.
On the synthetic benchmark from that bug stupid_memchr and bsd_memchr have the
same performance now when not inlining either function.
stupid_memchr: 323.0us
bsd_memchr: 321.0us
memchr: 479.0us
where memchr is the llvm-gcc compiled bsd_memchr from osx lion's libc. When
inlining is enabled bsd_memchr still regresses down to llvm-gcc memchr time,
I haven't fully understood the issue yet, something is grossly mangling the
loop after inlining.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158297 91177308-0d34-0410-b5e6-96231b3b80d8
Over the entire test-suite, this has an insignificantly negative average
performance impact, but reduces some of the worst slowdowns from the
anti-dep. change (r158294).
Largest speedups:
SingleSource/Benchmarks/Stanford/Quicksort - 28%
SingleSource/Benchmarks/Stanford/Towers - 24%
SingleSource/Benchmarks/Shootout-C++/matrix - 23%
MultiSource/Benchmarks/SciMark2-C/scimark2 - 19%
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount - 15%
(matrix and automotive-bitcount were both in the top-5 slowdown list from the
anti-dep. change)
Largest slowdowns:
MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 28%
MultiSource/Benchmarks/mediabench/gsm/toast/toast - 26%
MultiSource/Benchmarks/MiBench/automotive-susan/automotive-susan - 21%
SingleSource/Benchmarks/CoyoteBench/lpbench - 20%
MultiSource/Applications/d/make_dparser - 16%
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158296 91177308-0d34-0410-b5e6-96231b3b80d8
Using 'all' instead of 'critical' would be better because it would make it easier to
satisfy the bundling constraints, but, as noted in the FIXME, that is currently not
possible with the crs.
This yields an average 1% speedup over the entire test suite (on Power 7). Largest speedups:
SingleSource/Benchmarks/Shootout-C++/moments - 40%
MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 28%
SingleSource/Benchmarks/BenchmarkGame/nsieve-bits - 26%
SingleSource/Benchmarks/McGill/misr - 23%
MultiSource/Applications/JM/ldecod/ldecod - 22%
Largest slowdowns:
SingleSource/Benchmarks/Shootout-C++/matrix - -29%
SingleSource/Benchmarks/Shootout-C++/ary3 - -22%
MultiSource/Benchmarks/BitBench/uuencode/uuencode - -18%
SingleSource/Benchmarks/Shootout-C++/ary - -17%
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount - -15%
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158294 91177308-0d34-0410-b5e6-96231b3b80d8
The PPC64 backend had patterns for i32 <-> i64 extensions and truncations that
would leave self-moves in the final assembly. Replacing those patterns with ones
based on the SUBREG builtins yields better-looking code.
Thanks to Jakob and Owen for their suggestions in this matter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158283 91177308-0d34-0410-b5e6-96231b3b80d8
Tail merging had been disabled on PPC because it would disturb bundling decisions
made during pre-RA scheduling on the 970 cores. Now, however, all bundling decisions
are made during post-RA scheduling, and tail merging is generally beneficial (the
average test-suite speedup is insignificantly positive).
Largest test-suite speedups:
MultiSource/Benchmarks/mediabench/gsm/toast/toast - 30%
MultiSource/Benchmarks/BitBench/uuencode/uuencode - 23%
SingleSource/Benchmarks/Shootout-C++/ary - 21%
SingleSource/Benchmarks/Stanford/Queens - 17%
Largest slowdowns:
MultiSource/Benchmarks/MiBench/security-sha/security-sha - 24%
MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 22%
MultiSource/Applications/JM/ldecod/ldecod - 14%
MultiSource/Benchmarks/mediabench/g721/g721encode/encode - 9%
This is improved by using full (instead of just critical) anti-dependency breaking,
but doing so still causes miscompiles and so cannot yet be enabled by default.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158259 91177308-0d34-0410-b5e6-96231b3b80d8
The LiveRegMatrix represents the live range of assigned virtual
registers in a Live interval union per register unit. This is not
fundamentally different from the interference tracking in RegAllocBase
that both RABasic and RAGreedy use.
The important differences are:
- LiveRegMatrix tracks interference per register unit instead of per
physical register. This makes interference checks cheaper and
assignments slightly more expensive. For example, the ARM D7 reigster
has 24 aliases, so we would check 24 physregs before assigning to one.
With unit-based interference, we check 2 units before assigning to 2
units.
- LiveRegMatrix caches regmask interference checks. That is currently
duplicated functionality in RABasic and RAGreedy.
- LiveRegMatrix is a pass which makes it possible to insert
target-dependent passes between register allocation and rewriting.
Such passes could tweak the register assignments with interference
checking support from LiveRegMatrix.
Eventually, RABasic and RAGreedy will be switched to LiveRegMatrix.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158255 91177308-0d34-0410-b5e6-96231b3b80d8
This deduplicates some code from the optimizing register allocators, and
it means that it is now possible to change the register allocators'
solutions simply by editing the VirtRegMap between the register
allocator pass and the rewriter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158249 91177308-0d34-0410-b5e6-96231b3b80d8
OK, not really. We don't want to reintroduce the old rewriter hacks.
This patch extracts virtual register rewriting as a separate pass that
runs after the register allocator. This is possible now that
CodeGen/Passes.cpp can configure the full optimizing register allocator
pipeline.
The rewriter pass uses register assignments in VirtRegMap to rewrite
virtual registers to physical registers, and it inserts kill flags based
on live intervals.
These finalization steps are the same for the optimizing register
allocators: RABasic, RAGreedy, and PBQP.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158244 91177308-0d34-0410-b5e6-96231b3b80d8
The fast register allocator is not supposed to work in the optimizing
pipeline. It doesn't make sense to compute live intervals, run full copy
coalescing, and then run RAFast.
Fast register allocation in the optimizing pipeline is better done by
RABasic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158242 91177308-0d34-0410-b5e6-96231b3b80d8
-%a + 42
into
42 - %a
previously we were emitting:
-(%a + 42)
This fixes the infinite loop in PR12338. The generated code is still not perfect, though.
Will work on that next
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158237 91177308-0d34-0410-b5e6-96231b3b80d8
problem was that by moving instructions around inside the function, the pass
could accidentally move the iterator being used to advance over the function
too. Fix this by only processing the instruction equal to the iterator, and
leaving processing of instructions that might not be equal to the iterator
to later (later = after traversing the basic block; it could also wait until
after traversing the entire function, but this might make the sets quite big).
Original commit message:
Grab-bag of reassociate tweaks. Unify handling of dead instructions and
instructions to reoptimize. Exploit this to more systematically eliminate
dead instructions (this isn't very useful in practice but is convenient for
analysing some testcase I am working on). No need for WeakVH any more: use
an AssertingVH instead.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158226 91177308-0d34-0410-b5e6-96231b3b80d8
As Chris points out, this can now be removed!
TODO: check if the associated section on viterbi's inner loop can also be removed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158224 91177308-0d34-0410-b5e6-96231b3b80d8
Thanks to Jakob's help, this now causes no new test suite failures!
Over the entire test suite, this gives an average 1% speedup. The largest speedups are:
SingleSource/Benchmarks/Misc/pi - 108%
SingleSource/Benchmarks/CoyoteBench/lpbench - 54%
MultiSource/Benchmarks/Prolangs-C/unix-smail/unix-smail - 50%
SingleSource/Benchmarks/Shootout/ary3 - 32%
SingleSource/Benchmarks/Shootout-C++/matrix - 30%
The largest slowdowns are:
MultiSource/Benchmarks/mediabench/gsm/toast/toast - -30%
MultiSource/Benchmarks/Prolangs-C/bison/mybison - -25%
MultiSource/Benchmarks/BitBench/uuencode/uuencode - -22%
MultiSource/Applications/d/make_dparser - -14%
SingleSource/Benchmarks/Shootout-C++/ary - -13%
In light of these slowdowns, additional profiling work is obviously needed!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158223 91177308-0d34-0410-b5e6-96231b3b80d8
Marking these classes as non-alocatable allows CTR loop generation to
work correctly with the block placement passes, etc. These register
classes are currently used only by some unused TCRETURN patterns.
In future cleanup, these will be removed.
Thanks again to Jakob for suggesting this fix to the CTR loop problem!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158221 91177308-0d34-0410-b5e6-96231b3b80d8
This fixes an accidental dependence on static initialization order that I introduced yesterday.
Thank you Lang!!!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158215 91177308-0d34-0410-b5e6-96231b3b80d8
Bulk move of TargetInstrInfo implementation into
TargetInstrInfoImpl. This is dirty because the code isn't part of
TargetInstrInfoImpl class, nor should it be, because the methods are
not target hooks. However, it's the current mechanism for keeping
libTarget useful outside the backend. You'll get a not-so-nice link
error if you invoke a TargetInstrInfo method that depends on CodeGen.
The TargetInstrInfoImpl class should probably be removed since it
doesn't really solve this problem.
To really fix this, we probably need separate interfaces for the
CodeGen/nonCodeGen sides of TargetInstrInfo.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158212 91177308-0d34-0410-b5e6-96231b3b80d8
The pass itself works well, but the something in the Machine* infrastructure
does not understand terminators which define registers. Without the ability
to use the block-placement pass, etc. this causes performance regressions (and
so is turned off by default). Turning off the analysis turns off the problems
with the Machine* infrastructure.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158206 91177308-0d34-0410-b5e6-96231b3b80d8
The code which tests for an induction operation cannot assume that any
ADDI instruction will have a register operand because the operand could
also be a frame index; for example:
%vreg16<def> = ADDI8 <fi#0>, 0; G8RC:%vreg16
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158205 91177308-0d34-0410-b5e6-96231b3b80d8
This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon
pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are
no longer otherwise used. Also, invalid preheader DebugLoc is not used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158204 91177308-0d34-0410-b5e6-96231b3b80d8
can move instructions within the instruction list. If the instruction just
happens to be the one the basic block iterator is pointing to, and it is
moved to a different basic block, then we get into an infinite loop due to
the iterator running off the end of the basic block (for some reason this
doesn't fire any assertions). Original commit message:
Grab-bag of reassociate tweaks. Unify handling of dead instructions and
instructions to reoptimize. Exploit this to more systematically eliminate
dead instructions (this isn't very useful in practice but is convenient for
analysing some testcase I am working on). No need for WeakVH any more: use
an AssertingVH instead.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158199 91177308-0d34-0410-b5e6-96231b3b80d8
This was previously only done for executables and shared libraries, but not
for modules. As modules are essentially shared libraries (that need to be
dlopened explicitly), threating them the same as shared libraries seems
reasonable. This fixes the LLVM_BUILD_32_BITS build of Polly.
Contributed by: Ondra Hosek <ondra.hosek@gmail.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158195 91177308-0d34-0410-b5e6-96231b3b80d8
This patch will generate the following for integer ABS:
movl %edi, %eax
negl %eax
cmovll %edi, %eax
INSTEAD OF
movl %edi, %ecx
sarl $31, %ecx
leal (%rdi,%rcx), %eax
xorl %ecx, %eax
There exists a target-independent DAG combine for integer ABS, which converts
integer ABS to sar+add+xor. For X86, we match this pattern back to neg+cmov.
This is implemented in PerformXorCombine.
rdar://10695237
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158175 91177308-0d34-0410-b5e6-96231b3b80d8
