| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
EltsFromConsecutiveLoads
This patch adds support for trailing zero elements to VZEXT_LOAD loads (and checks that no zero elts occur within the consecutive load).
It also generalizes the 64-bit VZEXT_LOAD load matching to work for loads other than 2x32-bit loads.
After this patch it will also be easier to add support for other basic load patterns like 32-bit VZEXT_LOAD loads, PMOVZX and subvector load insertion.
Differential Revision: http://reviews.llvm.org/D16217
llvm-svn: 258798
|
| |
|
|
|
|
|
|
| |
Old intrinsics were forcing these, but they have now all
been removed. This fixes large i8 vector operations generally
being broken.
llvm-svn: 258788
|
| |
|
|
|
|
|
|
|
|
|
| |
I did my best to try to update all the uses in tests that
just happened to use the old ones to the newer intrinsics.
I'm not sure I got all of the immediate operand conversions
correct, since the value seems to have been ignored by the
old pattern but I don't think it really matters.
llvm-svn: 258787
|
| |
|
|
|
|
|
| |
More cleanup to try to get all intrinsics using the correct
amdgcn prefix that are as close to the instruction as possible.
llvm-svn: 258786
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Some of the special intrinsics now that now correspond to a instruction
also have special setting of some registers, e.g. llvm.SI.sendmsg sets
m0 as well as use s_sendmsg. Using these explicit register intrinsics
may be a better option.
Reading the exec mask and others may be useful for debugging. For this
I'm not sure this is entirely correct because we would want this to
be convergent, although it's possible this is already treated
sufficently conservatively.
llvm-svn: 258785
|
| |
|
|
|
|
| |
Also move into backend intrinsics to discourage use of the old name.
llvm-svn: 258783
|
| |
|
|
|
|
|
|
| |
These calls return their first argument, but because LLVM uses an intrinsic
with a void return type, they can't use the returned attribute. Generalize
the store results pass to optimize these calls too.
llvm-svn: 258781
|
| |
|
|
|
|
| |
Differential Revision: http://reviews.llvm.org/D16534
llvm-svn: 258779
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
For historic reasons, the behavior of .align differs between targets.
Fortunately, there are alternatives, .p2align and .balign, which make the
interpretation of the parameter explicit, and which behave consistently across
targets.
This patch teaches MC to use .p2align instead of .align, so that people reading
code for multiple architectures don't have to remember which way each platform
does its .align directive.
Differential Revision: http://reviews.llvm.org/D16549
llvm-svn: 258750
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
There's a special case in EmitLoweredSelect() that produces an improved
lowering for cmov(cmov) patterns. However this special lowering is
currently broken if the inner cmov has multiple users so this patch
stops using it in this case.
If you wonder why this wasn't fixed by continuing to use the special
lowering and inserting a 2nd PHI for the inner cmov: I believe this
would incur additional copies/register pressure so the special lowering
does not improve upon the normal one anymore in this case.
This fixes http://llvm.org/PR26256 (= rdar://24329747)
llvm-svn: 258729
|
| |
|
|
|
|
|
|
| |
Its main use is to allow memory folding of the 1st operand
Differential Revision: http://reviews.llvm.org/D16521
llvm-svn: 258726
|
| |
|
|
|
|
|
| |
Instructions can be DCE'd after the RegStackify pass. If the instruction which
would be the pop for what would be a push is removed, don't use a push.
llvm-svn: 258694
|
| |
|
|
| |
llvm-svn: 258693
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
When generating calls to memcpy, memmove, and memset, use void* as the return
type rather than void, to match the standard signatures for these functions.
This has no practical effect for most targets, since the return values of
these calls aren't being used anyway, and most calling conventions tolerate
this kind of mismatch. However, this change will help support future
optimizations to utilize the return value to avoid holding the argument
value live across a call.
llvm-svn: 258691
|
| |
|
|
|
|
| |
Differential Revision: http://reviews.llvm.org/D16520
llvm-svn: 258688
|
| |
|
|
|
|
| |
Differential Revision: http://reviews.llvm.org/D16519
llvm-svn: 258686
|
| |
|
|
|
|
|
|
| |
This patch was originally committed as r257885, but was reverted due to windows
failures. The cause of these failures has been fixed under r258677, hence
re-committing the original patch.
llvm-svn: 258683
|
| |
|
|
|
|
|
|
| |
This patch was originally committed as r257884, but was reverted due to windows
failures. The cause of these failures has been fixed under r258677, hence
re-committing the original patch.
llvm-svn: 258682
|
| |
|
|
|
|
|
|
|
|
|
| |
52bit integer
VPMADD52LUQ - Packed Multiply of Unsigned 52-bit Integers and Add the Low 52-bit Products to Qword Accumulators
VPMADD52HUQ - Packed Multiply of Unsigned 52-bit Unsigned Integers and Add High 52-bit Products to 64-bit Accumulators
Differential Revision: http://reviews.llvm.org/D16407
llvm-svn: 258680
|
| |
|
|
|
|
|
|
| |
Use AVX1 FP instructions (vmaskmovps/pd) in place of the AVX2 int instructions (vpmaskmovd/q).
Differential Revision: http://reviews.llvm.org/D16528
llvm-svn: 258675
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Changes in X86.td:
I set features of Intel processors in incremental form: IVB = SNB + X HSW = IVB + X ..
I added Skylake client processor and defined it's features
FeatureADX was missing on KNL
Added some new features to appropriate processors SMAP, IFMA, PREFETCHWT1, VMFUNC and others
Differential Revision: http://reviews.llvm.org/D16357
llvm-svn: 258659
|
| |
|
|
|
|
| |
Differential Revision: http://reviews.llvm.org/D16137
llvm-svn: 258657
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A cleanup can have paths which unwind or end up in unreachable.
If there is an unreachable path *and* a path which unwinds to caller,
we would mistakenly inject an unwind path to a catchswitch on the
unreachable path. This results in a verifier assertion firing because
the cleanup unwinds to two different places: to the caller and to the
catchswitch.
This occured because we used getCleanupRetUnwindDest to determine if the
cleanuppad had no cleanuprets.
This is incorrect, getCleanupRetUnwindDest returns null for cleanuprets
which unwind to caller.
llvm-svn: 258651
|
| |
|
|
|
|
| |
BUILD_VECTOR and UNDEF folding.
llvm-svn: 258646
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Previously, we would just output "foo = bar" in the assembly, and then
ptxas would choke. Now we die before emitting any invalid code.
Reviewers: echristo
Subscribers: jholewinski, llvm-commits, jhen, tra
Differential Revision: http://reviews.llvm.org/D16490
llvm-svn: 258638
|
| |
|
|
|
|
|
|
| |
For the moment, this file takes way too long to run (see inline comments), but
that should be a temporary problem. The fact that the compile time is so slow
for a target that doesn't support maskmov may be a bug worth investigating too.
llvm-svn: 258629
|
| |
|
|
|
|
| |
If the INSERTPS zeroes out all the referenced elements from either of the 2 input vectors (and the input is not already UNDEF), then set that input to UNDEF to reduce dependencies.
llvm-svn: 258622
|
| |
|
|
| |
llvm-svn: 258615
|
| |
|
|
| |
llvm-svn: 258614
|
| |
|
|
|
|
| |
This will make future test updates easier
llvm-svn: 258613
|
| |
|
|
|
|
| |
Replace tests with lrp with basic IR expansion
llvm-svn: 258612
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Some of the conditions necessary to produce ccmp sequences were only
checked in recursive calls to emitConjunctionDisjunctionTree() after
some of the earlier expressions were already built. Move all checks over
to isConjunctionDisjunctionTree() so they are all checked before we
start emitting instructions.
Also rename some variable to better reflect their usage.
llvm-svn: 258605
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Cleanups in C++ are a little weird. They are only guaranteed to be
reliably executed if, and only if, there is a viable catch handler which
can handle the exception.
This means that reachability of a cleanup is lexically determined by it
being nested with a try-block which unwinds to a catch. It is *cannot*
be reasoned about by examining the control flow edges leaving a cleanup.
Usually this is not a problem. It becomes a problem when there are *no*
edges out of a cleanup because we believed that code post-dominated by
the cleanup is dead. In LLVM's case, this code is what informs the
personality routine about the presence of a suitable catch handler.
However, the lack of edges to that catch handler makes the handler
become unreachable which causes us to remove it. By removing the
handler, the cleanup becomes unreachable.
Instead, inject a catch-all handler with every cleanup that has no
unwind edges. This will allow us to properly unwind the stack.
This fixes PR25997.
llvm-svn: 258580
|
| |
|
|
| |
llvm-svn: 258568
|
| |
|
|
| |
llvm-svn: 258558
|
| |
|
|
|
|
|
|
|
|
|
| |
The intrinsic target prefix should match the target name
as it appears in the triple.
This is not yet complete, but gets most of the important ones.
llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled
for compatability for now.
llvm-svn: 258557
|
| |
|
|
| |
llvm-svn: 258541
|
| |
|
|
|
|
|
|
| |
The promote alloca pass didn't handle these intrinsics and crashed.
These intrinsics should accept any address space, but for now just
erase them to avoid breaking.
llvm-svn: 258537
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Summary: Fixes PR26186.
Reviewers: grosser, jholewinski
Subscribers: jholewinski, llvm-commits
Differential Revision: http://reviews.llvm.org/D16479
llvm-svn: 258536
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The current behavior is incorrect, as the two CCs returned by
changeFPCCToAArch64CC, intended to be OR'ed, are instead used
in an AND ccmp chain.
Consider:
define i32 @t(float %a, float %b, float %c, float %d, i32 %e, i32 %f) {
%cc1 = fcmp one float %a, %b
%cc2 = fcmp olt float %c, %d
%and = and i1 %cc1, %cc2
%r = select i1 %and, i32 %e, i32 %f
ret i32 %r
}
Assuming (%a < %b) and (%c < %d); we used to do:
fcmp s0, s1 # nzcv <- 1000
orr w8, wzr, #0x1 # w8 <- 1
csel w9, w8, wzr, mi # w9 <- 1
csel w8, w8, w9, gt # w8 <- 1
fcmp s2, s3 # nzcv <- 1000
cset w9, mi # w9 <- 1
tst w8, w9 # (w8 & w9) == 1, so: nzcv <- 0000
csel w0, w0, w1, ne # w0 <- w0
We now do:
fcmp s2, s3 # nzcv <- 1000
fccmp s0, s1, #0, mi # mi, so: nzcv <- 1000
fccmp s0, s1, #8, le # !le, so: nzcv <- 1000
csel w0, w0, w1, pl # !pl, so: w0 <- w1
In other words, we transformed:
(c < d) && ((a < b) || (a > b))
into:
(c < d) && (a u>= b) && (a u<= b)
whereas, per De Morgan's, we wanted:
(c < d) && !((a u>= b) && (a u<= b))
Note that this problem doesn't occur in the test-suite.
changeFPCCToAArch64CC produces disjunct CCs; here, one -> mi/gt.
We can't represent that in the fccmp chain; it can't express
arbitrary OR sequences, as one comment explains:
In general we can create code for arbitrary "... (and (and A B) C)"
sequences. We can also implement some "or" expressions, because
"(or A B)" is equivalent to "not (and (not A) (not B))" and we can
implement some negation operations. [...] However there is no way
to negate the result of a partial sequence.
Instead, introduce changeFPCCToANDAArch64CC, which produces the
conjunct cond codes:
- (a one b)
== ((a olt b) || (a ogt b))
== ((a ord b) && (a une b))
- (a ueq b)
== ((a uno b) || (a oeq b))
== ((a ule b) && (a uge b))
Note that, at first, one might think that, when PushNegate is true,
we should use the disjunct CCs, in effect doing:
(a || b)
= !(!a && !(b))
= !(!a && !(b1 || b2)) <- changeFPCCToAArch64CC(b, b1, b2)
= !(!a && !b1 && !b2)
However, we can take advantage of the fact that the CC is already
negated, which lets us avoid special-casing PushNegate and doing
the simpler to reason about:
(a || b)
= !(!a && (!b))
= !(!a && (b1 && b2)) <- changeFPCCToANDAArch64CC(!b, b1, b2)
= !(!a && b1 && b2)
This makes both emitConditionalCompare cases behave identically,
and produces correct ccmp sequences for the 2-CC fcmps.
llvm-svn: 258533
|
| |
|
|
|
|
| |
Patch by Tobias Edler Von Koch.
llvm-svn: 258527
|
| |
|
|
|
|
| |
These ones aren't directly emitted by mesa and inserted by a pass.
llvm-svn: 258523
|
| |
|
|
|
|
|
| |
Mesa doesn't use this, and this is pattern matched already
from fsub x, (ffloor x)
llvm-svn: 258513
|
| |
|
|
|
|
|
|
| |
This reapplies r258296 and r258366, and also fixes an existing bug in
SelectionDAG.cpp's isMemSrcFromString, neglecting to account for the
offset in a GlobalAddressSDNode, which is uncovered by those patches.
llvm-svn: 258482
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
SETCC with f16 vectors has OperationAction set to Expand but still gets
lowered to FCM* intrinsics based on its result type. This patch skips
lowering of VSETCC if the operand is an f16 vector.
v4 and v8 tests included.
Reviewers: ab, jmolloy
Subscribers: srhines, llvm-commits
Differential Revision: http://reviews.llvm.org/D15361
llvm-svn: 258471
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
This reverts r258296 and the follow up r258366. With this change, we
miscompiled the following program on Windows:
#include <string>
#include <iostream>
static const char kData[] = "asdf jkl;";
int main() {
std::string s(kData + 3, sizeof(kData) - 3);
std::cout << s << '\n';
}
llvm-svn: 258465
|
| |
|
|
|
|
|
|
|
|
|
| |
The X86 musttail implementation finds register parameters to forward by
running the calling convention algorithm until a non-register location
is returned. However, assigning a vector memory location has the side
effect of increasing the function's stack alignment. We shouldn't
increase the stack alignment when we are only looking for register
parameters, so this change conditionalizes it.
llvm-svn: 258442
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Better handling of the annoying pshuflw/pshufhw ops which only shuffle lower/upper halves of a vector.
Added vXi16 unary shuffle support for cases where i16 elements (from the same half of the source) are being splatted to the whole of one of the halves. This avoids the general lowering case which must shuffle the 32-bit elements first - meaning that we used to end up with unnecessary duplicate pshuflw/pshufhw shuffles.
Note this has the side effect of a lot of SSSE3 test cases no longer needing to use PSHUFB, as it falls below the 3 op combine threshold for when PSHUFB is typically worth it. I've raised PR26183 to discuss if the threshold should be changed and whether we need to make it more specific to the target CPU.
Differential Revision: http://reviews.llvm.org/D14901
llvm-svn: 258440
|
| |
|
|
|
|
|
|
| |
Implemented intrinsic for the follow instructions (reg move) : VMOVDQU8/16, VMOVDQA32/64, VMOVAPS/PD.
Differential Revision: http://reviews.llvm.org/D16316
llvm-svn: 258398
|
| |
|
|
|
|
| |
Differential Revision: http://reviews.llvm.org/D16398
llvm-svn: 258397
|