| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
|
|
|
| |
llvm-svn: 306389
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
After this patch, we finally have test cases that require multiple
instruction emission.
Depends on D33590
Reviewers: ab, qcolombet, t.p.northover, rovka, kristof.beyls
Subscribers: javed.absar, llvm-commits, igorb
Differential Revision: https://reviews.llvm.org/D33596
llvm-svn: 306388
|
|
|
|
|
|
|
|
|
|
| |
* Mark as legal for (s32, i1, s32, s32)
* Map everything into GPRs
* Select to two instructions: a CMP of the condition against 0, to set
the flags, and a MOVCCr to select between the two inputs based on the
flags that we've just set
llvm-svn: 306382
|
|
|
|
|
|
| |
to surpress warnings. ppc970 should be 970 (or g5)
llvm-svn: 306380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
With scalar stores, M0 is clobbered and therefore marked as implicitly
defined. However, it is also dead.
This fixes an assertion when the Greedy Register Allocator decides to
optimize a spill/restore pair away again (via tryHintsRecoloring).
Reviewers: arsenm
Subscribers: qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D33319
llvm-svn: 306375
|
|
|
|
|
|
| |
G_FADD, G_FSUB, G_FMUL, G_FDIV. NFC.
llvm-svn: 306370
|
|
|
|
|
|
|
|
|
| |
PowerPC backend does not pass the current optimization level to SelectionDAGISel and so SelectionDAGISel works with the default optimization level regardless of the current optimization level.
This patch makes the PowerPC backend set the optimization level correctly.
Differential Revision: https://reviews.llvm.org/D34615
llvm-svn: 306367
|
|
|
|
|
|
|
|
|
| |
Remove invalid shortcut in fixupKills(): A register needs to be marked
live even when we are not adding a kill flag. This is because a
partially live register must not get a kill flags, but it still needs to
be fully marked live when walking backwards.
llvm-svn: 306352
|
|
|
|
|
|
|
|
|
|
|
|
| |
truncation and extension match.
This fixes PR33368.
Reviewer: rksimon
Differential Revision: https://reviews.llvm.org/D34069
llvm-svn: 306345
|
|
|
|
| |
llvm-svn: 306337
|
|
|
|
|
|
|
|
|
|
| |
Fixes bug 33597.
Use of substituteRegister in the tied operand case messes
up the register use iterator, causing some uses to be left
unprocessed.
llvm-svn: 306333
|
|
|
|
|
|
|
| |
This is the dual problem to legalizing G_INSERTs so most of the code and
testing was cribbed from there.
llvm-svn: 306328
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 306314
|
|
|
|
| |
llvm-svn: 306312
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
| |
Found several missed optimizations while investigating replacing _mm_mul_epi32/_mm_mul_epu32 with generic implementations
llvm-svn: 306302
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
|
|
|
|
| |
Reviewers: arsenm
Reviewed By: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D34589
llvm-svn: 306298
|
|
|
|
| |
llvm-svn: 306296
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 306288
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
| |
X86InterleavedAccess test.
Adding base tast (to trunk) for Store strid=4 vf=32.
llvm-svn: 306286
|
|
|
|
|
|
|
|
| |
Revert "[MBP] do not rotate loop if it creates extra branch"
It breaks the sanitizer build bots. Need to fix this.
llvm-svn: 306276
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 306246
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 306211
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 306199
|
|
|
|
|
|
|
| |
This should *really* be a llvm-mc test, but the parser is broken.
See PR33579 for the parser bug.
llvm-svn: 306198
|
|
|
|
|
|
| |
constants
llvm-svn: 306192
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
| |
llvm-svn: 306158
|
|
|
|
|
|
| |
This breaks passing of aligned function arguments.
llvm-svn: 306145
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
|
|
|
| |
I'm not sure yet why this wouldn't fail in the simple case,
but clearly I used the wrong value type with:
https://reviews.llvm.org/rL306040
...and the bug manifests with:
https://bugs.llvm.org/show_bug.cgi?id=33560
llvm-svn: 306139
|
|
|
|
|
|
| |
Check on slow/fast unaligned memory targets
llvm-svn: 306138
|
|
|
|
| |
llvm-svn: 306131
|
|
|
|
| |
llvm-svn: 306124
|
|
|
|
|
|
|
|
| |
It was trying to do too many things. The basic lumping together of values for
legalization purposes is now handled by G_MERGE_VALUES. More complex things
involving gaps and odd sizes are handled by G_INSERT sequences.
llvm-svn: 306120
|
|
|
|
|
|
|
|
| |
G_SEQUENCE is going away soon so as a first step the MachineIRBuilder needs to
be taught how to emulate it with alternatives. We use G_MERGE_VALUES where
possible, and a sequence of G_INSERTs if not.
llvm-svn: 306119
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts the use of TargetLowering::prepareVolatileOrAtomicLoad
introduced by r196905. Nothing in the semantics of the "volatile"
keyword or the definition of the z/Architecture actually requires
that volatile loads are preceded by a serialization operation, and
no other compiler on the platform actually implements this.
Since we've now seen a use case where this additional serialization
causes noticable performance degradation, this patch removes it.
The patch still leaves in the serialization before atomic loads,
which is now implemented directly in lowerATOMIC_LOAD. (This also
seems overkill, but that can be addressed separately.)
llvm-svn: 306117
|
|
|
|
| |
llvm-svn: 306114
|
|
|
|
| |
llvm-svn: 306113
|
|
|
|
|
|
|
|
|
|
|
|
| |
Reviewers: arsenm
Reviewed By: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D34349
llvm-svn: 306112
|
|
|
|
|
|
| |
r306109 was supposed to make this change, but I committed the wrong version.
llvm-svn: 306110
|