When we forward a stored value to a load and eliminate it entirely we need to
make sure the liveness of the register is maintained all the way to its use.
Previously we only cleared liveness on the store doing the forwarding, but
there could be other killing uses in between.
We already do the right thing when the load has to be converted into something
else, it was just this one path that skipped it.
llvm-svn: 306318
The recommit fixes three bugs: The first one is to use CurrentBlock instead of
PREInstr's Parent as param of performScalarPREInsertion because the Parent
of a clone instruction may be uninitialized. The second one is stop PRE when
CurrentBlock to its predecessor is a backedge and an operand of CurInst is
defined inside of CurrentBlock. The same value defined inside of loop in last
iteration can not be regarded as available. The third one is an out-of-bound
array access in a flipped if guard.
Right now scalarpre doesn't have phi-translate support, so it will miss some
simple pre opportunities. Like the following testcase, current scalarpre cannot
recognize the last "a * b" is fully redundent because a and b used by the last
"a * b" expr are both defined by phis.
long a[100], b[100], g1, g2, g3;
__attribute__((pure)) long goo();
void foo(long a, long b, long c, long d) {
g1 = a * b;
if (__builtin_expect(g2 > 3, 0)) {
a = c;
b = d;
g2 = a * b;
}
g3 = a * b; // fully redundant.
}
The patch adds phi-translate support in scalarpre. This is only a temporary
solution before the newpre based on newgvn is available.
llvm-svn: 306313
We sometimes need emergency spill slots for the register scavenger.
This may be the case when code needs to access a stack slot that
has an offset of 4096 or more relative to the stack pointer.
To make that determination, processFunctionBeforeFrameFinalized
currently simply checks the total stack frame size of the current
function. But this is not enough, since code may need to access
stack slots in the caller's stack frame as well, in particular
incoming arguments stored on the stack.
This commit fixes the problem by taking argument slots into account.
llvm-svn: 306305
The non-AVX-512 behavior was changed in r248266 to match N1778
(C bindings for IEEE-754 (2008)), which defined the four functions
to not raise the inexact exception ("rint" is still defined as raising
it).
Update the AVX-512 lowering of these functions to match that: it should
not be different.
llvm-svn: 306299
Convert vector increment or decrement to sub/add with an all-ones constant:
add X, <1, 1...> --> sub X, <-1, -1...>
sub X, <1, 1...> --> add X, <-1, -1...>
The all-ones vector constant can be materialized using a pcmpeq instruction that is
commonly recognized as an idiom (has no register dependency), so that's better than
loading a splat 1 constant.
AVX512 uses 'vpternlogd' for 512-bit vectors because there is apparently no better
way to produce 512 one-bits.
The general advantages of this lowering are:
1. pcmpeq has lower latency than a memop on every uarch I looked at in Agner's tables,
so in theory, this could be better for perf, but...
2. That seems unlikely to affect any OOO implementation, and I can't measure any real
perf difference from this transform on Haswell or Jaguar, but...
3. It doesn't look like it from the diffs, but this is an overall size win because we
eliminate 16 - 64 constant bytes in the case of a vector load. If we're broadcasting
a scalar load (which might itself be a bug), then we're replacing a scalar constant
load + broadcast with a single cheap op, so that should always be smaller/better too.
4. This makes the DAG/isel output more consistent - we use pcmpeq already for padd x, -1
and psub x, -1, so we should use that form for +1 too because we can. If there's some
reason to favor a constant load on some CPU, let's make the reverse transform for all
of these cases (either here in the DAG or in a later machine pass).
This should fix:
https://bugs.llvm.org/show_bug.cgi?id=33483
Differential Revision: https://reviews.llvm.org/D34336
llvm-svn: 306289
Csmith discovered that this function can be called with a zero argument,
in which case an assert for this triggered.
This patch also adds a guard before the other call to this function since
it was missing, although the test only covers the case where it was
discovered.
Reduced test case attached as CodeGen/SystemZ/int-cmp-54.ll.
Review: Ulrich Weigand
llvm-svn: 306287
This is a last fix for the corner case of PR32214. Actually this is not really corner case in general.
We should not do a loop rotation if we create an additional branch due to it.
Consider the case where we have a loop chain H, M, B, C , where
H is header with viable fallthrough from pre-header and exit from the loop
M - some middle block
B - backedge to Header but with exit from the loop also.
C - some cold block of the loop.
Let's H is determined as a best exit. If we do a loop rotation M, B, C, H we can introduce the extra branch.
Let's compute the change in number of branches:
+1 branch from pre-header to header
-1 branch from header to exit
+1 branch from header to middle block if there is such
-1 branch from cold bock to header if there is one
So if C is not a predecessor of H then we introduce extra branch.
This change actually prohibits rotation of the loop if both true
1) Best Exit has next element in chain as successor.
2) Last element in chain is not a predecessor of first element of chain.
Reviewers: iteratee, xur
Reviewed By: iteratee
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34271
llvm-svn: 306272
This should not be treated as a different version of
private_segment_buffer. These are distinct things with
different uses and register classes, and requires the
function argument info to have more context about the
function's type and environment.
Also add missing test coverage for the intrinsic, and
emit an error for HSA. This also encovers that the intrinsic
is broken unless there happen to be stack objects.
llvm-svn: 306264
This was reverted in r306252, but I already had the bug fixed and was
just trying to form a test case.
The original commit factored the logic for forming dedicated exits
inside of LoopSimplify into a helper that could be used elsewhere and
with an approach that required fewer intermediate data structures. See
that commit for full details including the change to the statistic, etc.
The code looked fine to me and my reviewers, but in fact didn't handle
indirectbr correctly -- it left the 'InLoopPredecessors' vector dirty.
If you have code that looks *just* right, you can end up leaking these
predecessors into a subsequent rewrite, and crash deep down when trying
to update PHI nodes for predecessors that don't exist.
I've added an assert that makes the bug much more obvious, and then
changed the code to reliably clear the vector so we don't get this bug
again in some other form as the code changes.
I've also added a test case that *does* manage to catch this while also
giving some nice positive coverage in the face of indirectbr.
The real code that found this came out of what I think is CPython's
interpreter loop, but any code with really "creative" interpreter loops
mixing indirectbr and other exit paths could manage to tickle the bug.
I was hard to reduce the original test case because in addition to
having a particular pattern of IR, the whole thing depends on the order
of the predecessors which is in turn depends on use list order. The test
case added here was designed so that in multiple different predecessor
orderings it should always end up going down the same path and tripping
the same bug. I hope. At least, it tripped it for me without
manipulating the use list order which is better than anything bugpoint
could do...
llvm-svn: 306257
I did some basic testing while looking for a bug in my recent change to
loop simplify and even though it didn't find the bug it seems like
a useful improvement anyways.
llvm-svn: 306256
http://rise4fun.com/Alive/i8Q
A narrow bitwise logic op is obviously better than math for value tracking,
and zext is better than sext. Typically, the 'not' will be folded into an
icmp predicate.
The IR difference would even survive through codegen for x86, so we would see
worse code:
https://godbolt.org/g/C14HMF
one_or_zero(int, int): # @one_or_zero(int, int)
xorl %eax, %eax
cmpl %esi, %edi
setle %al
retq
one_or_zero_alt(int, int): # @one_or_zero_alt(int, int)
xorl %ecx, %ecx
cmpl %esi, %edi
setg %cl
movl $1, %eax
subl %ecx, %eax
retq
llvm-svn: 306243
The compiler fails with assertion during legalization of SETCC for <3 x i8> operands.
The result is extended to <4 x i8> and then truncated <4 x i1>. It does not happen on AVX2, because the final result of SETCC is <4 x i32>.
Differential Revision: https://reviews.llvm.org/D34503
llvm-svn: 306242
Summary:
Support vector type G_EXTRACT selection. For now G_EXTRACT marked as legal for any type, so nothing to do in legalizer.
Split from https://reviews.llvm.org/D33665
Reviewers: qcolombet, t.p.northover, zvi, guyblank
Reviewed By: guyblank
Subscribers: guyblank, rovka, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D33957
llvm-svn: 306240
The cost of an interleaved access was only implemented for AVX512. For other
X86 targets an overly conservative Base cost was returned, resulting in
avoiding vectorization where it is actually profitable to vectorize.
This patch starts to add costs for AVX2 for most prominent cases of
interleaved accesses (stride 3,4 chars, for now).
Note1: Improvements of up to ~4x were observed in some of EEMBC's rgb
workloads; There is also a known issue of 15-30% degradations on some of these
workloads, associated with an interleaved access followed by type
promotion/widening; the resulting shuffle sequence is currently inefficient and
will be improved by a series of patches that extend the X86InterleavedAccess pass
(such as D34601 and more to follow).
Note 2: The costs in this patch do not reflect port pressure penalties which can
be very dominant in the case of interleaved accesses since most of the shuffle
operations are restricted to a single port. Further tuning, that may incorporate
these considerations, will be done on top of the upcoming improved shuffle
sequences (that is, along with the abovementioned work to extend
X86InterleavedAccess pass).
Differential Revision: https://reviews.llvm.org/D34023
llvm-svn: 306238
When SelectionDAG expands memcpy (or memmove) call into a sequence of load and store instructions, it disregards dereferenceable flag even the source pointer is known to be dereferenceable.
This results in an assertion failure if SelectionDAG commonizes a load instruction generated for memcpy with another load instruction for the source pointer.
This patch makes SelectionDAG to set the dereferenceable flag for the load instructions properly to avoid the assertion failure.
Differential Revision: https://reviews.llvm.org/D34467
llvm-svn: 306209
Summary:
InstCombine replaces large allocas with small globals consts causing buffer overflows
on valid code, see PR33372.
This fix permits this optimization only if the global is dereference for alloca size.
Fixes PR33372
Reviewers: eugenis, majnemer, chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34311
llvm-svn: 306194
processFixupValue is called on every relaxation iteration. applyFixup
is only called once at the very end. applyFixup is then the correct
place to do last minute changes and value checks.
While here, do proper range checks again for fixup_arm_thumb_bl. We
used to do it, but dropped because of thumb2. We now do it again, but
use the thumb2 range.
llvm-svn: 306177
After fixing (r306173) a failing test in the lld test suite (r306173),
reland r306095.
Original commit message:
[mips] Fix register positions in the aui/daui instructions
Swapped the position of the rt and rs register in the aui/daui
instructions for mips32r6 and mips64r6. With this change, the format of
the generated instructions complies with specifications and GCC.
Patch by Milos Stojanovic.
llvm-svn: 306174
We would return an error in getVaPtr if the RVA table being dumped was
the last data in the .rdata section. Avoid the issue by subtracting one
from the offset and adding it back to get an open interval again.
llvm-svn: 306171
Summary:
Without this patch some types have incorrect size and/or alignment
according to the MSP430 EABI.
Reviewers: asl, awygle
Reviewed By: asl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34561
llvm-svn: 306159
This is useful when you want to look at a specific chunk of a
stream or look for discontinuities, and you need to know the
list of blocks occupied by a stream.
llvm-svn: 306150
This patch dumps the raw bytes of the pdb name map which contains
the mapping of stream name to stream index for the string table
and other reserved streams.
llvm-svn: 306148
Normally we can only make sense of the content of a PDB in terms
of streams and blocks, but in some cases it may be useful to dump
bytes at a specific absolute file offset. For example, if you
know that some interesting data is at a particular location and
you want to see some surrounding data.
llvm-svn: 306146
This patch contains a pass that transforms CBZ/CBNZ/TBZ/TBNZ instructions into a
conditional branch (Bcc), when the NZCV flags can be set for "free". This is
preferred on targets that have more flexibility when scheduling Bcc
instructions as compared to CBZ/CBNZ/TBZ/TBNZ (assuming all other variables are
equal). This can reduce register pressure and is also the default behavior for
GCC.
A few examples:
add w8, w0, w1 -> cmn w0, w1 ; CMN is an alias of ADDS.
cbz w8, .LBB_2 -> b.eq .LBB0_2 ; single def/use of w8 removed.
add w8, w0, w1 -> adds w8, w0, w1 ; w8 has multiple uses.
cbz w8, .LBB1_2 -> b.eq .LBB1_2
sub w8, w0, w1 -> subs w8, w0, w1 ; w8 has multiple uses.
tbz w8, #31, .LBB6_2 -> b.ge .LBB6_2
In looking at all current sub-target machine descriptions, this transformation
appears to be either positive or neutral.
Differential Revision: https://reviews.llvm.org/D34220.
llvm-svn: 306144
The goal here is to make it possible to display absolute
file offsets when dumping byets from an MSF. The problem is
that when dumping bytes from an MSF, often the bytes will
cross a block boundary and encounter a discontinuity. We
can't use the normal formatBinary() function for this because
this would just treat the sequence as entirely ascending, and
not account out-of-order blocks.
This patch adds a formatMsfData() function to our printer, and
then uses this function to improve the output of the -stream-data
command line option for dumping bytes from a particular stream.
Test coverage is also expanded to make sure to include all possible
scenarios of offsets, sizes, and crossing block boundaries.
llvm-svn: 306141