This header includes CodeGen headers, and is not, itself, included by
any Target headers, so move it into CodeGen to match the layering of its
implementation.
llvm-svn: 317647
Summary:
This just seems to have been an oversight. We already supported the f64
atomic add with an explicit scope (e.g. "cta"), but not the scopeless
version.
Reviewers: tra
Subscribers: jholewinski, sanjoy, cfe-commits, llvm-commits, hiraditya
Differential Revision: https://reviews.llvm.org/D39638
llvm-svn: 317623
An "or" that sets the sign-bit can be replaced with a "xor", if
the sign-bit was known to be clear before. With some changes to
instruction combining, the simple sign-bit check was failing.
Replace it with a more flexible one to catch more cases.
llvm-svn: 317592
Patch [5/5] in a series to add assembler/disassembler support for AArch64 SVE unpredicated ADD/SUB instructions.
Patch by Sander De Smalen.
Reviewed by: rengolin
Differential Revision: https://reviews.llvm.org/D39091
llvm-svn: 317591
Patch [3/5] in a series to add assembler/disassembler support for AArch64 SVE unpredicated ADD/SUB instructions.
To summarise, this patch adds:
* SVE register definitions
* Methods to parse SVE register operands
* Methods to print SVE register operands
* RegKind SVEDataVector to distinguish it from other data types like scalar register or Neon vector.
* k_SVEDataRegister and SVEDataRegOp to describe SVE registers (which will be extended by further patches with e.g. ElementWidth and the shift-extend type).
Patch by Sander De Smalen.
Reviewed by: rengolin
Differential Revision: https://reviews.llvm.org/D39089
llvm-svn: 317590
Patch [4/5] in a series to add assembler/disassembler support for AArch64 SVE unpredicated ADD/SUB instructions.
We add SVE as unsupported feature for CPUs that don't have SVE to prevent errors from scheduler models saying it lacks information for these instructions.
Patch by Sander De Smalen.
Reviewed by: rengolin
Differential Revision: https://reviews.llvm.org/D39090
llvm-svn: 317582
Reland r317100 with minor fix regarding ComputeCommonTailLength function in
BranchFolding.cpp. Skipping top CFI instructions block needs to executed on
several more return points in ComputeCommonTailLength().
Original r317100 message:
"Correct dwarf unwind information in function epilogue for X86"
This patch aims to provide correct dwarf unwind information in function
epilogue for X86.
It consists of two parts. The first part inserts CFI instructions that set
appropriate cfa offset and cfa register in emitEpilogue() in
X86FrameLowering. This part is X86 specific.
The second part is platform independent and ensures that:
- CFI instructions do not affect code generation
- Unwind information remains correct when a function is modified by
different passes. This is done in a late pass by analyzing information
about cfa offset and cfa register in BBs and inserting additional CFI
directives where necessary.
Changed CFI instructions so that they:
- are duplicable
- are not counted as instructions when tail duplicating or tail merging
- can be compared as equal
Added CFIInstrInserter pass:
- analyzes each basic block to determine cfa offset and register valid at
its entry and exit
- verifies that outgoing cfa offset and register of predecessor blocks match
incoming values of their successors
- inserts additional CFI directives at basic block beginning to correct the
rule for calculating CFA
Having CFI instructions in function epilogue can cause incorrect CFA
calculation rule for some basic blocks. This can happen if, due to basic
block reordering, or the existence of multiple epilogue blocks, some of the
blocks have wrong cfa offset and register values set by the epilogue block
above them.
CFIInstrInserter is currently run only on X86, but can be used by any target
that implements support for adding CFI instructions in epilogue.
Patch by Violeta Vukobrat.
llvm-svn: 317579
Summary:
The cost calculation for default case on X86 target does not always
follow correct wayt because of missing 4-th argument in
`BaseT::getCastInstrCost()` call. Added this missing parameter.
Reviewers: hfinkel, mkuper, RKSimon, spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39687
llvm-svn: 317576
Patch [2/5] in a series to add assembler/disassembler support for AArch64 SVE unpredicated ADD/SUB instructions.
This change is a non functional change that adds RegKind as an alternative to 'isVector' to prepare it for newer types (SVE data vectors and predicate vectors) that will be added in next patches (where the SVE data vector is added as part of this patch set)
Patch by Sander De Smalen.
Reviewed by: rengolin
Differential Revision: https://reviews.llvm.org/D39088
llvm-svn: 317569
This changes the interface of how targets describe how to legalize, see
the below description.
1. Interface for targets to describe how to legalize.
In GlobalISel, the API in the LegalizerInfo class is the main interface
for targets to specify which types are legal for which operations, and
what to do to turn illegal type/operation combinations into legal ones.
For each operation the type sizes that can be legalized without having
to change the size of the type are specified with a call to setAction.
This isn't different to how GlobalISel worked before. For example, for a
target that supports 32 and 64 bit adds natively:
for (auto Ty : {s32, s64})
setAction({G_ADD, 0, s32}, Legal);
or for a target that needs a library call for a 32 bit division:
setAction({G_SDIV, s32}, Libcall);
The main conceptual change to the LegalizerInfo API, is in specifying
how to legalize the type sizes for which a change of size is needed. For
example, in the above example, how to specify how all types from i1 to
i8388607 (apart from s32 and s64 which are legal) need to be legalized
and expressed in terms of operations on the available legal sizes
(again, i32 and i64 in this case). Before, the implementation only
allowed specifying power-of-2-sized types (e.g. setAction({G_ADD, 0,
s128}, NarrowScalar). A worse limitation was that if you'd wanted to
specify how to legalize all the sized types as allowed by the LLVM-IR
LangRef, i1 to i8388607, you'd have to call setAction 8388607-3 times
and probably would need a lot of memory to store all of these
specifications.
Instead, the legalization actions that need to change the size of the
type are specified now using a "SizeChangeStrategy". For example:
setLegalizeScalarToDifferentSizeStrategy(
G_ADD, 0, widenToLargerAndNarrowToLargest);
This example indicates that for type sizes for which there is a larger
size that can be legalized towards, do it by Widening the size.
For example, G_ADD on s17 will be legalized by first doing WidenScalar
to make it s32, after which it's legal.
The "NarrowToLargest" indicates what to do if there is no larger size
that can be legalized towards. E.g. G_ADD on s92 will be legalized by
doing NarrowScalar to s64.
Another example, taken from the ARM backend is:
for (unsigned Op : {G_SDIV, G_UDIV}) {
setLegalizeScalarToDifferentSizeStrategy(Op, 0,
widenToLargerTypesUnsupportedOtherwise);
if (ST.hasDivideInARMMode())
setAction({Op, s32}, Legal);
else
setAction({Op, s32}, Libcall);
}
For this example, G_SDIV on s8, on a target without a divide
instruction, would be legalized by first doing action (WidenScalar,
s32), followed by (Libcall, s32).
The same principle is also followed for when the number of vector lanes
on vector data types need to be changed, e.g.:
setAction({G_ADD, LLT::vector(8, 8)}, LegalizerInfo::Legal);
setAction({G_ADD, LLT::vector(16, 8)}, LegalizerInfo::Legal);
setAction({G_ADD, LLT::vector(4, 16)}, LegalizerInfo::Legal);
setAction({G_ADD, LLT::vector(8, 16)}, LegalizerInfo::Legal);
setAction({G_ADD, LLT::vector(2, 32)}, LegalizerInfo::Legal);
setAction({G_ADD, LLT::vector(4, 32)}, LegalizerInfo::Legal);
setLegalizeVectorElementToDifferentSizeStrategy(
G_ADD, 0, widenToLargerTypesUnsupportedOtherwise);
As currently implemented here, vector types are legalized by first
making the vector element size legal, followed by then making the number
of lanes legal. The strategy to follow in the first step is set by a
call to setLegalizeVectorElementToDifferentSizeStrategy, see example
above. The strategy followed in the second step
"moreToWiderTypesAndLessToWidest" (see code for its definition),
indicating that vectors are widened to more elements so they map to
natively supported vector widths, or when there isn't a legal wider
vector, split the vector to map it to the widest vector supported.
Therefore, for the above specification, some example legalizations are:
* getAction({G_ADD, LLT::vector(3, 3)})
returns {WidenScalar, LLT::vector(3, 8)}
* getAction({G_ADD, LLT::vector(3, 8)})
then returns {MoreElements, LLT::vector(8, 8)}
* getAction({G_ADD, LLT::vector(20, 8)})
returns {FewerElements, LLT::vector(16, 8)}
2. Key implementation aspects.
How to legalize a specific (operation, type index, size) tuple is
represented by mapping intervals of integers representing a range of
size types to an action to take, e.g.:
setScalarAction({G_ADD, LLT:scalar(1)},
{{1, WidenScalar}, // bit sizes [ 1, 31[
{32, Legal}, // bit sizes [32, 33[
{33, WidenScalar}, // bit sizes [33, 64[
{64, Legal}, // bit sizes [64, 65[
{65, NarrowScalar} // bit sizes [65, +inf[
});
Please note that most of the code to do the actual lowering of
non-power-of-2 sized types is currently missing, this is just trying to
make it possible for targets to specify what is legal, and how non-legal
types should be legalized. Probably quite a bit of further work is
needed in the actual legalizing and the other passes in GlobalISel to
support non-power-of-2 sized types.
I hope the documentation in LegalizerInfo.h and the examples provided in the
various {Target}LegalizerInfo.cpp and LegalizerInfoTest.cpp explains well
enough how this is meant to be used.
This drops the need for LLT::{half,double}...Size().
Differential Revision: https://reviews.llvm.org/D30529
llvm-svn: 317560
Summary:
Calls using invoke in funclet based functions are assumed to clobber
all registers, which causes the stack adjustment using pops to consider
all registers not defined by the call to be undefined, which can
unfortunately include the base pointer, if one is needed.
To prevent this (and possibly other hazards), skip reserved registers
when looking for candidate registers.
This fixes issue #45034 in the Rust compiler.
Reviewers: mkuper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39636
llvm-svn: 317551
This combine was already done in two places. The
generic combiner already has done this since
r217610, for adds (with a single use).
This one was added in r303641, and added support for handling
or as well. r313251 later added support to the generic
combine for or. It also turns out the isOrEquivalentToAdd
check is not necessary for this combine.
Additionally, we already reproduce this combine in yet
another place in the backend, although in that version
multiple uses of the add are still folded if it will
allow a fold into the addressing mode. That version needs
to be improved to understand ors though, as well as the
correct legal offsets for private.
llvm-svn: 317526
The EVEX to VEX pass is already assuming this is true under AVX512VL. We had special patterns to use zmm instructions if VLX and F16C weren't available.
Instead just make AVX512 imply F16C to make the EVEX to VEX behavior explicitly legal and remove the extra patterns.
All known CPUs with AVX512 have F16C so this should safe for now.
llvm-svn: 317521
Previously our VEX patterns were checking Subtarget.hasFMA() which checked FMA || AVX512. So we were behaving as if AVX512 implied it anyway. Which means we'd allow VEX encoded 128/256 FMA when AVX512F was enabled but AVX512VL is off. Regardless of the FMA flag.
EVEX to VEX also transforms scalar EVEX FMA instructions to their VEX versions even without the FMA flag. Similarly for 128/256 under AVX512VL.
So this makes AVX512 imply FeatureFMA to make our current behavior explicit.
All known CPUs that support AVX512 have VEX FMA instructions.
llvm-svn: 317520
As discussed on llvm-dev:
http://lists.llvm.org/pipermail/llvm-dev/2016-November/107104.html
and again more recently:
http://lists.llvm.org/pipermail/llvm-dev/2017-October/118118.html
...this is a step in cleaning up our fast-math-flags implementation in IR to better match
the capabilities of both clang's user-visible flags and the backend's flags for SDNode.
As proposed in the above threads, we're replacing the 'UnsafeAlgebra' bit (which had the
'umbrella' meaning that all flags are set) with a new bit that only applies to algebraic
reassociation - 'AllowReassoc'.
We're also adding a bit to allow approximations for library functions called 'ApproxFunc'
(this was initially proposed as 'libm' or similar).
...and we're out of bits. 7 bits ought to be enough for anyone, right? :) FWIW, I did
look at getting this out of SubclassOptionalData via SubclassData (spacious 16-bits),
but that's apparently already used for other purposes. Also, I don't think we can just
add a field to FPMathOperator because Operator is not intended to be instantiated.
We'll defer movement of FMF to another day.
We keep the 'fast' keyword. I thought about removing that, but seeing IR like this:
%f.fast = fadd reassoc nnan ninf nsz arcp contract afn float %op1, %op2
...made me think we want to keep the shortcut synonym.
Finally, this change is binary incompatible with existing IR as seen in the
compatibility tests. This statement:
"Newer releases can ignore features from older releases, but they cannot miscompile
them. For example, if nsw is ever replaced with something else, dropping it would be
a valid way to upgrade the IR."
( http://llvm.org/docs/DeveloperPolicy.html#ir-backwards-compatibility )
...provides the flexibility we want to make this change without requiring a new IR
version. Ie, we're not loosening the FP strictness of existing IR. At worst, we will
fail to optimize some previously 'fast' code because it's no longer recognized as
'fast'. This should get fixed as we audit/squash all of the uses of 'isFast()'.
Note: an inter-dependent clang commit to use the new API name should closely follow
commit.
Differential Revision: https://reviews.llvm.org/D39304
llvm-svn: 317488
We still early-out for X86ISD::PEXTRW/X86ISD::PEXTRB so no actual change in behaviour, but it'll make it easier to add support in a future patch.
llvm-svn: 317485
combineExtractWithShuffle can handle more complex shuffles/bitcasts than we can with the equivalent code in XFormVExtractWithShuffleIntoLoad.
Mainly a compile time improvement now (combineExtractWithShuffle combines will have always failed late on inside XFormVExtractWithShuffleIntoLoad), and will let us merge combineExtractVectorElt_SSE in a future commit.
llvm-svn: 317481
SystemZ can do division and remainder in a single instruction for scalar
integer types, which are now reflected by returning true in this hook for
those cases.
Review: Ulrich Weigand
llvm-svn: 317477
The backend assumes pointer in default addr space is 32 bit, which is not
true for the new addr space mapping and causes assertion for unresolved
functions.
This patch fixes that.
Differential Revision: https://reviews.llvm.org/D39643
llvm-svn: 317476
Previously, the 'movep' instruction was defined for microMIPS32r3 and
shared that definition with microMIPS32R6. 'movep' was re-encoded for
microMIPS32r6, so this patch provides the correct encoding.
Secondly, correct the encoding of the 'rs' and 'rt' operands which have
an instruction specific encoding for the registers those operands accept.
Finally, correct the decoding of the 'dst_regs' operand which was extracting
the relevant field from the instruction, but was actually extracting the
field from the alreadly extracted field.
Reviewers: atanasyan
Differential Revision: https://reviews.llvm.org/D39495
llvm-svn: 317475
Recommit:
This patch contains update of the costs of interleaved loads of v8f32 of stride 3 and 8.
fixed the location of the lit test it works with make check-all.
Differential Revision: https://reviews.llvm.org/D39403
llvm-svn: 317471
Mark all symbols involved with TLS relocations as being TLS symbols.
This resolves PR35140.
Thanks to Alex Crichton for reporting the issue!
Reviewers: atanasyan
Differential Revision: https://reviews.llvm.org/D39591
llvm-svn: 317470
Added TESTM and TESTNM to the list of instructions that already zeroing unused upper bits
and does not need the redundant shift left and shift right instructions afterwards.
Added a pattern for TESTM and TESTNM in iselLowering, so now icmp(neq,and(X,Y), 0) goes folds into TESTM
and icmp(eq,and(X,Y), 0) goes folds into TESTNM
This commit is a preparation for lowering the test and testn X86 intrinsics to IR.
Differential Revision: https://reviews.llvm.org/D38732
llvm-svn: 317465
Summary:
Try to lower a BUILD_VECTOR composed of extract-extract chains that can be
reasoned to be a permutation of a vector by indices in a non-constant vector.
We saw this pattern created by ISPC, which resolts to creating it due to the
requirement that shufflevector's mask operand be a *constant* vector.
I didn't check this but we could possibly use this pattern for lowering the X86 permute
C-instrinsics instead of llvm.x86 instrinsics.
This change can be followed by more improvements:
1. Handle vectors with undef elements.
2. Utilize pshufb and zero-mask-blending to support more effiecient
construction of vectors with constant-0 elements.
3. Use smaller-element vectors of same width, and "interpolate" the indices,
when no native operation available.
Reviewers: RKSimon, craig.topper
Reviewed By: RKSimon
Subscribers: chandlerc, DavidKreitzer
Differential Revision: https://reviews.llvm.org/D39126
llvm-svn: 317463
This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR.
Differential Revision: https://reviews.llvm.org/D38684
Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540
llvm-svn: 317458
Next step is to use them for the legacy FMA scalar intrinsics as well. This will enable the legacy intrinsics to use EVEX encoded opcodes and the extended registers.
llvm-svn: 317453
reverted my changes will be committed later after fixing the failure
This patch contains update of the costs of interleaved loads of v8f32 of stride 3 and 8.
Differential Revision: https://reviews.llvm.org/D39403
llvm-svn: 317433
This patch contains update of the costs of interleaved loads of v8f32 of stride 3 and 8.
Differential Revision: https://reviews.llvm.org/D39403
llvm-svn: 317432
Summary:
AVX512 added RCP14 and RSQRT instructions which improve accuracy over the legacy RCP and RSQRT instruction, but not enough accuracy to remove the need for a Newton Raphson refinement.
Currently we use these new instructions for the legacy packed SSE instrinics, but not the scalar instrinsics. And we use it for fast math optimization of division and reciprocal sqrt.
I think switching the legacy instrinsics maybe surprising to the user since it changes the answer based on which processor you're using regardless of any fastmath settings. It's also weird that we did something different between scalar and packed.
As far at the reciprocal estimation, I think it creates unnecessary deltas in our output behavior (and prevents EVEX->VEX). A little playing around with gcc and icc and godbolt suggest they don't change which instructions they use here.
This patch adds new X86ISD nodes for the RCP14/RSQRT14 and uses those for the new intrinsics. Leaving the old intrinsics to use the old instructions.
Going forward I think our focus should be on
-Supporting 512-bit vectors, which will have to use the RCP14/RSQRT14.
-Using RSQRT28/RCP28 to remove the Newton Raphson step on processors with AVX512ER
-Supporting double precision.
Reviewers: zvi, DavidKreitzer, RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39583
llvm-svn: 317413