This was intended to undo the sub canonicalization in cases where it's not profitable, but it also
finds some cases on it's own.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147256 91177308-0d34-0410-b5e6-96231b3b80d8
unsigned foo(unsigned x) { return 31 - __builtin_clz(x); }
now compiles into a single "bsrl" instruction on x86.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147255 91177308-0d34-0410-b5e6-96231b3b80d8
This has the obvious advantage of being commutable and is always a win on x86 because
const - x wastes a register there. On less weird architectures this may lead to
a regression because other arithmetic doesn't fuse with it anymore. I'll address that
problem in a followup.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147254 91177308-0d34-0410-b5e6-96231b3b80d8
LZCNT instructions are available. Force promotion to i32 to get
a smaller encoding since the fix-ups necessary are just as complex for
either promoted type
We can't do standard promotion for CTLZ when lowering through BSR
because it results in poor code surrounding the 'xor' at the end of this
instruction. Essentially, if we promote the entire CTLZ node to i32, we
end up doing the xor on a 32-bit CTLZ implementation, and then
subtracting appropriately to get back to an i8 value. Instead, our
custom logic just uses the knowledge of the incoming size to compute
a perfect xor. I'd love to know of a way to fix this, but so far I'm
drawing a blank. I suspect the legalizer could be more clever and/or it
could collude with the DAG combiner, but how... ;]
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147251 91177308-0d34-0410-b5e6-96231b3b80d8
'bsf' instructions here.
This one is actually debatable to my eyes. It's not clear that any chip
implementing 'tzcnt' would have a slow 'bsf' for any reason, and unless
EFLAGS or a zero input matters, 'tzcnt' is just a longer encoding.
Still, this restores the old behavior with 'tzcnt' enabled for now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147246 91177308-0d34-0410-b5e6-96231b3b80d8
X86ISelLowering C++ code. Because this is lowered via an xor wrapped
around a bsr, we want the dagcombine which runs after isel lowering to
have a chance to clean things up. In particular, it is very common to
see code which looks like:
(sizeof(x)*8 - 1) ^ __builtin_clz(x)
Which is trying to compute the most significant bit of 'x'. That's
actually the value computed directly by the 'bsr' instruction, but if we
match it too late, we'll get completely redundant xor instructions.
The more naive code for the above (subtracting rather than using an xor)
still isn't handled correctly due to the dagcombine getting confused.
Also, while here fix an issue spotted by inspection: we should have been
expanding the zero-undef variants to the normal variants when there is
an 'lzcnt' instruction. Do so, and test for this. We don't want to
generate unnecessary 'bsr' instructions.
These two changes fix some regressions in encoding and decoding
benchmarks. However, there is still a *lot* to be improve on in this
type of code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147244 91177308-0d34-0410-b5e6-96231b3b80d8
ARM targets with NEON units have access to aligned vector loads and
stores that are potentially faster than unaligned operations.
Add support for spilling the callee-saved NEON registers to an aligned
stack area using 16-byte aligned NEON loads and store.
This feature is off by default, controlled by an -align-neon-spills
command line option.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147211 91177308-0d34-0410-b5e6-96231b3b80d8
My change r146949 added register clobbers to the eh_sjlj_dispatchsetup pseudo
instruction, but on Thumb1 some of those registers cannot be used. This
caused massive failures on the testsuite when compiling for Thumb1. While
fixing that, I noticed that the eh_sjlj_setjmp instruction has a "nofp"
variant, and I realized that dispatchsetup needs the same thing, so I have
added that as well.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147204 91177308-0d34-0410-b5e6-96231b3b80d8
The value from the operands isn't right yet, but we weren't encoding it at
all previously. The parser needs to twiddle the values when building the
instruction.
Partial for: rdar://10558523
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147170 91177308-0d34-0410-b5e6-96231b3b80d8
probability wouldn't be considered "hot" in some weird loop structures
or other compounding probability patterns. This makes it much harder to
confuse, but isn't really a principled fix. I'd actually like it if we
could model a zero probability, as it would make this much easier to
reason about. Suggestions for how to do this better are welcome.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147142 91177308-0d34-0410-b5e6-96231b3b80d8
performance regressions (both execution-time and compile-time) on our
nightly testers.
Original commit message:
Fix for bug #11429: Wrong behaviour for switches. Small improvement for code
size heuristics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147131 91177308-0d34-0410-b5e6-96231b3b80d8
Rather than require the symbol to be explicitly an argument of the directive,
allow it to look ahead and grab the symbol from the next non-whitespace
line.
rdar://10611140
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147100 91177308-0d34-0410-b5e6-96231b3b80d8
Diagnostics are now emitted via the SourceMgr and we use MemoryBuffer
for buffer management. Switched the code to make use of the trailing
'0' that MemoryBuffer guarantees where it makes sense.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147063 91177308-0d34-0410-b5e6-96231b3b80d8
call site of an intrinsic is also not an inline candidate. While here, make it
more obvious that this code ignores all intrinsics. Noticed by inspection!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147037 91177308-0d34-0410-b5e6-96231b3b80d8
DSHD (Double Swap Halfwords within Doublewords). Add a pattern which replaces
64-bit bswap with a DSBH and DSHD pair.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147017 91177308-0d34-0410-b5e6-96231b3b80d8
instruction supported by mips32r2, and add a pattern which replaces bswap with
a ROTR and WSBH pair.
WSBW is removed since it is not an instruction the current architectures
support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147015 91177308-0d34-0410-b5e6-96231b3b80d8
the build bot in some cases. The basic issue happens when a source module contains
both a "%foo" type and a "%foo.42" type. It will see the later one, check to see if
the destination module contains a "%foo" type, and it will return true... because
both the source and destination modules are in the same LLVMContext. We don't want
to map source types to other source types, so don't do the remapping if the mapped
type came from the source module.
Unfortunately, I've been unable to reduce a decent testcase for this, kc++ is
pretty great that way.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147010 91177308-0d34-0410-b5e6-96231b3b80d8
Use the spill slot alignment as well as the local variable alignment to
determine when the stack needs to be realigned. This works now that the
ARM target can always realign the stack by using a base pointer.
Still respect the ARMBaseRegisterInfo::canRealignStack() function
vetoing a realigned stack. Don't use aligned spill code in that case.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146997 91177308-0d34-0410-b5e6-96231b3b80d8
use the zero-undefined variants of CTTZ and CTLZ. These are just simple
patterns for now, there is more to be done to make real world code using
these constructs be optimized and codegen'ed properly on X86.
The existing tests are spiffed up to check that we no longer generate
unnecessary cmov instructions, and that we generate the very important
'xor' to transform bsr which counts the index of the most significant
one bit to the number of leading (most significant) zero bits. Also they
now check that when the variant with defined zero result is used, the
cmov is still produced.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146974 91177308-0d34-0410-b5e6-96231b3b80d8
Pulling the template implementation into the header to guarantee
that it's visible to all possible instantiations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146973 91177308-0d34-0410-b5e6-96231b3b80d8
We used to rely on the *eh_sjlj_setjmp instructions to mark that a function
with setjmp/longjmp exception handling clobbers all the registers. But with
the recent reorganization of ARM EH, those eh_sjlj_setjmp instructions are
expanded away earlier, before PEI can see them to determine what registers to
save and restore. Mark the dispatchsetup instruction in the same way, since
that instruction cannot be expanded early. This also more accurately reflects
when the registers are clobbered.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146949 91177308-0d34-0410-b5e6-96231b3b80d8
"mov r1, r2, lsl #0" should assemble as "mov r1, r2" even though it's
not strictly legal UAL syntax. It's a common extension and the friendly
thing to do.
rdar://10604663
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146937 91177308-0d34-0410-b5e6-96231b3b80d8
merging types by name when we can. We still don't guarantee type name linkage
but we do it when obviously the right thing to do. This makes LTO type names
easier to read, for example.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146932 91177308-0d34-0410-b5e6-96231b3b80d8
unpredicated. That is, turn
subeq r0, r1, #1
addne r0, r1, #1
into
sub r0, r1, #1
addne r0, r1, #1
For targets where conditional instructions are always executed, this may be
beneficial. It may remove pseudo anti-dependency in out-of-order execution
CPUs. e.g.
op r1, ...
str r1, [r10] ; end-of-life of r1 as div result
cmp r0, #65
movne r1, #44 ; raw dependency on previous r1
moveq r1, #12
If movne is unpredicated, then
op r1, ...
str r1, [r10]
cmp r0, #65
mov r1, #44 ; r1 written unconditionally
moveq r1, #12
Both mov and moveq are no longer depdendent on the first instruction. This gives
the out-of-order execution engine more freedom to reorder them.
This has passed entire LLVM test suite. But it has not been enabled for any ARM
variant pending more performance evaluation.
rdar://8951196
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146914 91177308-0d34-0410-b5e6-96231b3b80d8
This change reduces the number of instructions generated.
For example,
(load (add (sub $n0, $n1), (MipsLo got(s))))
results in the following sequence of instructions:
1. sub $n2, $n0, $n1
2. lw got(s)($n2)
Previously, three instructions were needed.
1. sub $n2, $n0, $n1
2. addiu $n3, $n2, got(s)
3. lw 0($n3)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146888 91177308-0d34-0410-b5e6-96231b3b80d8