Each Calling convention (CC) defines a static list of registers that should be preserved by a callee function. All other registers should be saved by the caller.
Some CCs use additional condition: If the register is used for passing/returning arguments – the caller needs to save it - even if it is part of the Callee Saved Registers (CSR) list.
The current LLVM implementation doesn’t support it. It will save a register if it is part of the static CSR list and will not care if the register is passed/returned by the callee.
The solution is to dynamically allocate the CSR lists (Only for these CCs). The lists will be updated with actual registers that should be saved by the callee.
Since we need the allocated lists to live as long as the function exists, the list should reside inside the Machine Register Info (MRI) which is a property of the Machine Function and managed by it (and has the same life span).
The lists should be saved in the MRI and populated upon LowerCall and LowerFormalArguments.
The patch will also assist to implement future no_caller_saved_regsiters attribute intended for interrupt handler CC.
Differential Revision: https://reviews.llvm.org/D28566
llvm-svn: 297715
getIntrinsicInstrCost() used to only compute scalarization cost based on types.
This patch improves this so that the actual arguments are checked when they are
available, in order to handle only unique non-constant operands.
Tests updates:
Analysis/CostModel/X86/arith-fp.ll
Transforms/LoopVectorize/AArch64/interleaved_cost.ll
Transforms/LoopVectorize/ARM/interleaved_cost.ll
The improvement in getOperandsScalarizationOverhead() to differentiate on
constants made it necessary to update the interleaved_cost.ll tests even
though they do not relate to intrinsics.
Review: Hal Finkel
https://reviews.llvm.org/D29540
llvm-svn: 297705
rL230225 made the assumption that only the lower 32-bits of an MMX register load is used as a shift value, when in fact the whole 64-bits are reloaded and treated as a i64 to determine the shift value.
This patch reverts rL230225 to ensure that the whole 64-bits of memory are folded and ensures that the upper 32-bit are zero'd for cases where the shift value has come from a scalar source.
Found during fuzz testing.
Differential Revision: https://reviews.llvm.org/D30833
llvm-svn: 297667
I am leaving the code in clang which filters mxcsr from the clobber list because that is still technically correct and will be useful again when the MXCSR register is reintroduced.
llvm-svn: 297664
This commit adds tail call support to the MachineOutliner pass. This allows
the outliner to insert jumps rather than calls in areas where tail calling is
possible. Outlined tail calls include the return or terminator of the basic
block being outlined from.
Tail call support allows the outliner to take returns and terminators into
consideration while finding candidates to outline. It also allows the outliner
to save more instructions. For example, in the X86-64 outliner, a tail called
outlined function saves one instruction since no return has to be inserted.
llvm-svn: 297653
For AVX-512 we force the input to zero if the input is undef or the mask is all ones to break an execution dependency. This patch brings the same behavior to AVX2.
llvm-svn: 297652
We were already forcing undef inputs to become a zero vector, this now catches an all ones mask too.
Ideally we'd use undef and let execution dep fix handle picking the best register/clearance for the undef, but I don't think it can handle the early clobber today.
llvm-svn: 297651
The immediate should be 1 or 2, not 0 or 1. This was found while adding bounds checking to clang. In fact the existing clang builtin test failed if we ran it all the way to assembly.
llvm-svn: 297591
I noticed unnecessary 'sbb' instructions in D30472 and while looking at 'ptest' codegen recently.
This happens because we were transforming any 'setb' - even when we only wanted a single-bit result.
This patch moves those transforms under visitAdd/visitSub, so we we're only creating sbb/adc when it
is a win. I don't know why we need a SETCC_CARRY node type, but I'm not proposing to change that
existing behavior in this patch.
Also, I'm skeptical that sbb/adc are a win for all micro-arches, so I added comments to the test files
where this transform still fires.
The test changes here are all cases where we no longer produce sbb/adc. Avoiding partial register
stalls (generating an xor to clear a register) is not handled in some cases, but that's a separate
issue.
Differential Revision: https://reviews.llvm.org/D30611
llvm-svn: 297586
I'm pretty sure there are more problems lurking here. But I think this fixes PR32241.
I've added the test case from that bug and added asserts that will fail if we ever try to copy between high registers and mask registers again.
llvm-svn: 297574
Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte.
This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte.
Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate?
Differential Revision: https://reviews.llvm.org/D29841
llvm-svn: 297568
This only requires a 64-bit memory source, not the whole 128-bits. But the 128-bit case is still supported via X86InstrInfo::foldMemoryOperandImpl
llvm-svn: 297523
In order to make it easier to parse information about the performance of
MacroFusion, this patch adds the function and the instruction names to the
debug output of this pass.
llvm-svn: 297504
We currently have to insert bits via a temporary variable of the same size as the target with various shift/mask stages, resulting in further temporary variables, all of which require the allocation of memory for large APInts (MaskSizeInBits > 64).
This is another of the compile time issues identified in PR32037 (see also D30265).
This patch adds the APInt::insertBits() helper method which avoids the temporary memory allocation and masks/inserts the raw bits directly into the target.
Differential Revision: https://reviews.llvm.org/D30780
llvm-svn: 297458
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
The problem with the previous commit appears to have been that TableGen was including CodeGen/LowLevelType.h instead of Support/LowLevelTypeImpl.h.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
llvm-svn: 297241
More module problems. This time it only showed up in the stage 2 compile of
clang-x86_64-linux-selfhost-modules-2 but not the stage 1 compile.
Somehow, this change causes the build to need Attributes.gen before it's been
generated.
llvm-svn: 297188
Summary:
Loop alignment can cause a significant change of
the perfromance for short loops.
To be able to evaluate the impact of loop alignment this change
introduces the new option x86-experimental-pref-loop-alignment.
The alignment will be 2^Value bytes, the default value is 4.
Patch by Serguei Katkov!
Reviewers: craig.topper
Reviewed By: craig.topper
Subscribers: sanjoy, llvm-commits
Differential Revision: https://reviews.llvm.org/D30391
llvm-svn: 297178
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
llvm-svn: 297177
X86EvexToVex machine instruction pass compresses EVEX encoded instructions by replacing them with their identical VEX encoded instructions when possible.
It uses manually supported 2 large tables that map the EVEX instructions to their VEX ideticals.
This TableGen backend replaces the tables by automatically generating them.
Differential Revision: https://reviews.llvm.org/D30451
llvm-svn: 297127
evex2vex pass defines 2 tables which maps EVEX instructions to their VEX identical when possible. Adding all missing entries.
Differential Revision: https://reviews.llvm.org/D30501
llvm-svn: 297126
A bit more painful than G_INSERT because it was more widely used, but this
should simplify the handling of extract operations in most locations.
llvm-svn: 297100
Fixed the asan bot failure which led to the last commit of the outliner being reverted.
The change is in lib/CodeGen/MachineOutliner.cpp in the SuffixTree's constructor. LeafVector
is no longer initialized using reserve but just a standard constructor.
llvm-svn: 297081
Use the store size of the argument type, which will be a byte-sized
quantity, rather than dividing the size in bits by 8.
Fixes PR32136 and re-enables copy elision from i64 arguments.
Reverts the workaround in from r296950.
llvm-svn: 297045
As described on PR31712, we miss a variety of legalization combines because we lower these to X86ISD::VSEXT/VZEXT despite them having the same functionality. This patch makes 128-bit (SSE41) SIGN/ZERO_EXTEND_VECTOR_IN_REG ops legal, adds the necessary tablegen plumbing and uses a helper 'getExtendInVec' to decide when to use SIGN/ZERO_EXTEND_VECTOR_IN_REG or VSEXT/VZEXT.
We're missing a couple of shuffle combines that will be added in a future patch for review.
Later patches can then support the AVX2 cases as a mixture of SIGN/ZERO_EXTEND and SIGN/ZERO_EXTEND_VECTOR_IN_REG, and then finally deal with the AVX512 cases.
Differential Revision: https://reviews.llvm.org/D30549
llvm-svn: 296985
The larger goal is to move the ADC/SBB transforms currently in
combineX86SetCC() to combineAddOrSubToADCOrSBB() because we're
creating ADC/SBB in lots of places where we shouldn't.
This was intended to be an NFC change, but avx-512 has something
strange going on. It doesn't seem like any of the affected tests
should really be using SET+TEST or ADC; a simple ADD could replace
several instructions. But that's another bug...
llvm-svn: 296978
select Cond, C +/- 1, C --> add(ext Cond), C -- with a target hook.
This is part of the ongoing process to obsolete D24480. The motivation is to
canonicalize to select IR in InstCombine whenever possible, so we need to have a way to
undo that easily in codegen.
PowerPC is an obvious winner for this kind of transform because it has fast and complete
bit-twiddling abilities but generally lousy conditional execution perf (although this might
have changed in recent implementations).
x86 also sees some wins, but the effect is limited because these transforms already mostly
exist in its target-specific combineSelectOfTwoConstants(). The fact that we see any x86
changes just shows that that code is a mess of special-case holes. We may be able to remove
some of that logic now.
My guess is that other targets will want to enable this hook for most cases. The likely
follow-ups would be to add value type and/or the constants themselves as parameters for the
hook. As the tests in select_const.ll show, we can transform any select-of-constants to
math/logic, but the general transform for any 2 constants needs one more instruction
(multiply or 'and').
ARM is one target that I think may not want this for most cases. I see infinite loops there
because it wants to use selects to enable conditionally executed instructions.
Differential Revision: https://reviews.llvm.org/D30537
llvm-svn: 296977
Long ago (2010 according to svn blame), combineShuffle probably needed to prevent the accidental creation of illegal i64 types but there doesn't appear to be any combines that can cause this any more as they all have their own legality checks.
Differential Revision: https://reviews.llvm.org/D30213
llvm-svn: 296966
This fixes cases where i1 types were not properly legalized yet and lead
to the creating of 0-sized stack slots.
This fixes http://llvm.org/PR32136
llvm-svn: 296950
The comments were wrong, and this is not an obvious transform.
This hopefully makes it clearer that we're missing the commuted
patterns for adds. It's less clear that this is actually a good
transform for all micro-arch.
This is prep work for trying to clean up the current adc/sbb
codegen because it's definitely not happening optimally.
llvm-svn: 296918
VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be.
Differential Revision: https://reviews.llvm.org/D29874
llvm-svn: 296859
MMX extraction often ends up as extract_i32(bitcast_v2i32(extract_i64(bitcast_v1i64(x86mmx v), 0)), 0) which fails to simplify on 32-bit targets as i64 isn't legal
llvm-svn: 296782
Summary:
Avoids tons of prologue boilerplate when arguments are passed in memory
and left in memory. This can happen in a debug build or in a release
build when an argument alloca is escaped. This will dramatically affect
the code size of x86 debug builds, because X86 fast isel doesn't handle
arguments passed in memory at all. It only handles the x86_64 case of up
to 6 basic register parameters.
This is implemented by analyzing the entry block before ISel to identify
copy elision candidates. A copy elision candidate is an argument that is
used to fully initialize an alloca before any other possibly escaping
uses of that alloca. If an argument is a copy elision candidate, we set
a flag on the InputArg. If the the target generates loads from a fixed
stack object that matches the size and alignment requirements of the
alloca, the SelectionDAG builder will delete the stack object created
for the alloca and replace it with the fixed stack object. The load is
left behind to satisfy any remaining uses of the argument value. The
store is now dead and is therefore elided. The fixed stack object is
also marked as mutable, as it may now be modified by the user, and it
would be invalid to rematerialize the initial load from it.
Supersedes D28388
Fixes PR26328
Reviewers: chandlerc, MatzeB, qcolombet, inglorion, hans
Subscribers: igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D29668
llvm-svn: 296683
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
llvm-svn: 296474
This is a patch for the outliner described in the RFC at:
http://lists.llvm.org/pipermail/llvm-dev/2016-August/104170.html
The outliner is a code-size reduction pass which works by finding
repeated sequences of instructions in a program, and replacing them with
calls to functions. This is useful to people working in low-memory
environments, where sacrificing performance for space is acceptable.
This adds an interprocedural outliner directly before printing assembly.
For reference on how this would work, this patch also includes X86
target hooks and an X86 test.
The outliner is run like so:
clang -mno-red-zone -mllvm -enable-machine-outliner file.c
Patch by Jessica Paquette<jpaquette@apple.com>!
rdar://29166825
Differential Revision: https://reviews.llvm.org/D26872
llvm-svn: 296418
DAGCombiner already supports peeking thorough shuffles to improve vector element extraction, but legalization often leaves us in situations where we need to extract vector elements after shuffles have already been lowered.
This patch adds support for VECTOR_EXTRACT_ELEMENT/PEXTRW/PEXTRB instructions to attempt to handle target shuffles as well. I've covered some basic scenarios including handling shuffle mask scaling and the implicit zero-extension of PEXTRW/PEXTRB, there is more that could be done here (that I've mentioned in TODOs) but I haven't found many cases where its worth it.
Differential Revision: https://reviews.llvm.org/D30176
llvm-svn: 296381
Summary:
SmallBitVector uses a malloc for more than 58 bits on a 64-bit target and more than 27 bits on a 32-bit target. Some of the vector types we deal with here use more than those number of elements and therefore cause a malloc.
APInt on the other hand supports up to 64 bits without a malloc. That's the maximum number of bits we need here so we can avoid a malloc for all cases by using APInt.
Reviewers: RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30392
llvm-svn: 296355
Summary:
SmallBitVector uses a malloc for more than 58 bits on a 64-bit target and more than 27 bits on a 32-bit target. Some of the vector types we deal with here use more than those number of elements and therefore cause a malloc.
APInt on the other hand supports up to 64 bits without a malloc. That's the maximum number of bits we need here so we can avoid a malloc for all cases by using APInt.
Reviewers: RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30390
llvm-svn: 296354
Some of the vectors are under sized to avoid heap allocation. In one case the vector was oversized.
Differential Revision: https://reviews.llvm.org/D30387
llvm-svn: 296353
Summary:
SmallBitVector uses a malloc for more than 58 bits on a 64-bit target and more than 27 bits on a 32-bit target. Some of the vector types we deal with here use more than those number of elements and therefore cause a malloc.
APInt on the other hand supports up to 64 bits without a malloc. That's the maximum number of bits we need here so we can avoid a malloc for all cases by using APInt. This will incur a minor increase in stack usage due to APInt storing the bit count separately from the data bits unlike SmallBitVector, but that should be ok.
Reviewers: RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30386
llvm-svn: 296352
The current pattern for extract bits in range is typically:
Mask.lshr(BitOffset).trunc(SubSizeInBits);
Which can be particularly slow for large APInts (MaskSizeInBits > 64) as they require the allocation of memory for the temporary variable.
This is another of the compile time issues identified in PR32037 (see also D30265).
This patch adds the APInt::extractBits() helper method which avoids the temporary memory allocation.
Differential Revision: https://reviews.llvm.org/D30336
llvm-svn: 296272
The current pattern for extract bits in range is typically:
Mask.lshr(BitOffset).trunc(SubSizeInBits);
Which can be particularly slow for large APInts (MaskSizeInBits > 64) as they require the allocation of memory for the temporary variable.
This is another of the compile time issues identified in PR32037 (see also D30265).
This patch adds the APInt::extractBits() helper method which avoids the temporary memory allocation.
Differential Revision: https://reviews.llvm.org/D30336
llvm-svn: 296147
The current pattern for extract bits in range is typically:
Mask.lshr(BitOffset).trunc(SubSizeInBits);
Which can be particularly slow for large APInts (MaskSizeInBits > 64) as they require the allocation of memory for the temporary variable.
This is another of the compile time issues identified in PR32037 (see also D30265).
This patch adds the APInt::extractBits() helper method which avoids the temporary memory allocation.
Differential Revision: https://reviews.llvm.org/D30336
llvm-svn: 296141
Noticed while profiling PR32037, the target shuffle ops were being stored in SmallVector<*,8> types but the combiner could store as many as 16 ops at maximum depth (2 per depth).
llvm-svn: 296130
The current pattern for setting bits in range is typically:
Mask |= APInt::getBitsSet(MaskSizeInBits, LoPos, HiPos);
Which can be particularly slow for large APInts (MaskSizeInBits > 64) as they require the allocation memory for the temporary variable.
This is one of the key compile time issues identified in PR32037.
This patch adds the APInt::setBits() helper method which avoids the temporary memory allocation completely, this first implementation uses setBit() internally instead but already significantly reduces the regression in PR32037 (~10% drop). Additional optimization may be possible.
I investigated whether there is need for APInt::clearBits() and APInt::flipBits() equivalents but haven't seen these patterns to be particularly common, but reusing the code would be trivial.
Differential Revision: https://reviews.llvm.org/D30265
llvm-svn: 296102
The Fuchsia ABI defines slots from the thread pointer where the
stack-guard value for stack-protector, and the unsafe stack pointer
for safe-stack, are stored. This parallels the Android ABI support.
Patch by Roland McGrath
Differential Revision: https://reviews.llvm.org/D30237
llvm-svn: 296081
AVX versions of the converts work on f32/f64 types, while AVX512 version work on vectors.
Differential Revision: https://reviews.llvm.org/D29988
llvm-svn: 295940
Minor optimization, don't create temporary mask APInts that are just going to be OR'd into the accumulate masks - insert directly instead.
llvm-svn: 295848
This patch introduces new X86ISD::FMAXS and X86ISD::FMINS opcodes. The legacy intrinsics now lower to this node. As do the AVX-512 masked intrinsics when the rounding mode is CUR_DIRECTION.
I've merged a copy of the tablegen multiclass avx512_fp_scalar into avx512_fp_scalar_sae. avx512_fp_scalar still needs to support CUR_DIRECTION appearing as a rounding mode for X86ISD::FADD_ROUND and others.
Differential revision: https://reviews.llvm.org/D30186
llvm-svn: 295810
Summary:
Rework the code that was sinking/duplicating (icmp and, 0) sequences
into blocks where they were being used by conditional branches to form
more tbz instructions on AArch64. The new code is more general in that
it just looks for 'and's that have all icmp 0's as users, with a target
hook used to select which subset of 'and' instructions to consider.
This change also enables 'and' sinking for X86, where it is more widely
beneficial than on AArch64.
The 'and' sinking/duplicating code is moved into the optimizeInst phase
of CodeGenPrepare, where it can take advantage of the fact the
OptimizeCmpExpression has already sunk/duplicated any icmps into the
blocks where they are used. One minor complication from this change is
that optimizeLoadExt needed to be updated to always mark 'and's it has
determined should be in the same block as their feeding load in the
InsertedInsts set to avoid an infinite loop of hoisting and sinking the
same 'and'.
This change fixes a regression on X86 in the tsan runtime caused by
moving GVNHoist to a later place in the optimization pipeline (see
PR31382).
Reviewers: t.p.northover, qcolombet, MatzeB
Subscribers: aemerson, mcrosier, sebpop, llvm-commits
Differential Revision: https://reviews.llvm.org/D28813
llvm-svn: 295746
This matches what is already done during shuffle lowering and helps prevent the need for a zero-vector in cases where shuffles match both patterns.
llvm-svn: 295723
Summary:
Sandy Bridge and later CPUs have better throughput using a SHLD to implement rotate versus the normal rotate instructions. Additionally it saves one uop and avoids a partial flag update dependency.
This patch implements this change on any Sandy Bridge or later processor without BMI2 instructions. With BMI2 we will use RORX as we currently do.
Reviewers: zvi
Reviewed By: zvi
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30181
llvm-svn: 295697
Pull out repeated code for extraction index operand and source vector value type.
Use isNullConstant helper to check for zero extraction index.
llvm-svn: 295670
Its more profitable to go through memory (1 cycles throughput)
than using VMOVD + VPERMV/PSHUFB sequence ( 2/3 cycles throughput) to implement EXTRACT_VECTOR_ELT with variable index.
IACA tool was used to get performace estimation (https://software.intel.com/en-us/articles/intel-architecture-code-analyzer)
For example for var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8 test from vector-shuffle-variable-128.ll I get 26 cycles vs 79 cycles.
Removing the VINSERT node, we don't need it any more.
Differential Revision: https://reviews.llvm.org/D29690
llvm-svn: 295660
Add WIG value to all of AVX instructions which ignore the W-bit in their encoding, instead of giving them the default value of 0.
This patch is needed for a follow up work on EVEX2VEX pass (replacing EVEX encoded instructions with their corresponding VEX version when possible).
Differential Revision: https://reviews.llvm.org/D29876
llvm-svn: 295643
Replaces existing approach that could only search BUILD_VECTOR nodes.
Requires getTargetConstantBitsFromNode to discriminate cases with all/partial UNDEF bits in each element - this should also be useful when we get around to supporting getTargetShuffleMaskIndices with UNDEF elements.
llvm-svn: 295613
As discussed on D27692, this permits another domain to be used to combine a shuffle at high depths.
We currently set the required depth at 4 or more combined shuffles, this is probably too high for most targets but is a good starting point and already helps avoid a number of costly variable shuffles.
llvm-svn: 295608
Add the infrastructure to flag whether float and/or int domains are permitable.
A future patch will enable domain crossing based off shuffle depth and the value types of the source vectors.
llvm-svn: 295604
The instructions are marked commutable, but without special handling we don't get the immediate correct.
While here also remove the masked memory forms that aren't commutable.
llvm-svn: 295602
This requires some instructions to be renamed to move the Y earlier in the instruction name. The new names are more consistent with other instructions.
llvm-svn: 295579
It seems we were already upgrading 128-bit VPCMOV, but the intrinsic was still defined and being used in isel patterns. While I was here I also simplified the tablegen multiclasses.
llvm-svn: 295564
The original commit was reverted in r283329 due to a miscompile in
Chromium. That turned out to be the same issue as PR31257, which was
fixed in r295262.
llvm-svn: 295357
The existing code always saves the xmm registers for 64-bit targets even if the
target doesn't support SSE (which is common for kernels). Thus, the compiler
inserts movaps instructions which lead to CPU exceptions when an interrupt
handler is invoked.
This commit fixes this bug by returning a register set without xmm registers
from getCalleeSavedRegs and getCallPreservedMask for such targets.
Patch by Philipp Oppermann.
Differential Revision: https://reviews.llvm.org/D29959
llvm-svn: 295347
The new 512-bit unmasked intrinsics will make it easy to handle these with the SSE/AVX intrinsics in InstCombine where we currently have a TODO.
llvm-svn: 295290
This reverts r294348, which removed support for conditional tail calls
due to the PR above. It fixes the PR by marking live registers as
implicitly used and defined by the now predicated tailcall. This is
similar to how IfConversion predicates instructions.
Differential Revision: https://reviews.llvm.org/D29856
llvm-svn: 295262
Minor performance speedup - if any call to getShuffleScalarElt fails to get a result, don't both calling for the remaining elements as EltsFromConsecutiveLoads will fail anyhow.
llvm-svn: 295235
Summary:
We don't seem to have great rules on what a valid VBROADCAST node looks like. And as a consequence we end up with a lot of patterns to try to catch everything. We have patterns with scalar inputs, 128-bit vector inputs, 256-bit vector inputs, and 512-bit vector inputs.
As you can see from the things improved here we are currently missing patterns for 128-bit loads being extended to 256-bit before the vbroadcast.
I'd like to propose that VBROADCAST should always take a 128-bit vector type as input. As a first step towards that this patch adds an EXTRACT_SUBVECTOR in front of VBROADCAST when the input is 256 or 512-bits. In the future I would like to add scalar_to_vector around all the scalar operations. And maybe we should consider adding a VBROADCAST+load node to avoid separating loads from the broadcasting operation when the load itself isn't foldable.
This requires an additional change in target shuffle combining to look for the extract subvector and look through it to find the original operand. I'm sure this change isn't perfect but was enough to fix a few test failures that were being caused.
Another interesting thing I noticed is that the changes in masked_gather_scatter.ll show cases were we don't remove a useless insert into element 1 before broadcasting element 0.
Reviewers: delena, RKSimon, zvi
Reviewed By: zvi
Subscribers: igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D28747
llvm-svn: 295155
This adds MXCSR to the set of recognized registers for X86 targets and updates the instructions that read or write it. I do not intend for all of the various floating point instructions that implicitly use the control bits or update the status bits of this register to ever have that usage modeled by default. However, when constrained floating point modes (such as strict FP exception status modeling or dynamic rounding modes) are enabled, implicit use/def information for MXCSR will be added to those instructions.
Until those additional updates are made this should cause (almost?) no functional changes. Theoretically, this will prevent instructions like LDMXCSR and STMXCSR from being moved past one another, but that should be prevented anyway and I haven't found a case where it is happening now.
Differential Revision: https://reviews.llvm.org/D29903
llvm-svn: 295004
We now detect that both the extract and insert indices are non-zero and convert to a shuffle. This will be lowered as a blend for 256-bit vectors or as a vshuf operations for 512-bit vectors.
llvm-svn: 294931
This results in the simplifications inside of getNode running while we're legalizing nodes popped off the worklist during the final DAG combine. This basically makes a DAG combine like operation occur during this legalize step, but we don't handle something quite the same way. I think we don't recursively added the removed nodes to the DAG combiner worklist.
llvm-svn: 294929
I can't prove that we can select this instruction or the AVX/SSE version, but I'm adding it for consistency for now so I can continue matching the load folding tables.
llvm-svn: 294907
The target shuffle match function arguments were using the term 'Ops' but the function names referred to them as 'Inputs' - use 'Inputs' consistently.
llvm-svn: 294900
Initial 256-bit vector support - 512-bit support requires extra checks for AVX512BW support (PMOVZXBW) that will be handled in a future patch.
llvm-svn: 294896
Removes duplicate constant extraction code in getTargetShuffleMaskIndices.
getTargetConstantBitsFromNode - adds support for VZEXT_MOVL(SCALAR_TO_VECTOR) and fail if the caller doesn't support undef bits.
llvm-svn: 294856
Seems the execution dependency pass likes to use FP instructions when most of the consuming code is integer if a vextractf128 instruction produced the register. Without AVX2 we don't have the corresponding integer instruction available.
This patch suppresses the domain on these instructions to GenericDomain if AVX2 is not supported so that they are ignored by domain fixing. If AVX2 is supported we'll report the correct domain and allow them to switch between integer and fp.
Overall I think this produces better results in the modified test cases.
llvm-svn: 294824
Since r274013, we've been looking through bitcasts on broadcast inputs.
In the scalar-folding case (from a load, build_vector, or sc2vec),
the input type didn't matter, as we'd simply bitcast the resulting
scalar back.
However, when broadcasting a 128-bit-lane-aligned element, we create an
EXTRACT_SUBVECTOR. Use proper types, by creating an extract_subvector
of the original input type.
llvm-svn: 294774
In some cases we call getTargetConstantBitsFromNode for nodes that haven't been lowered from BUILD_VECTOR yet
Note: We're getting very close to being able to move most of the constant extraction code from getTargetShuffleMaskIndices into getTargetConstantBitsFromNode
llvm-svn: 294746
until we can get better TargetMachine::isCompatibleDataLayout to compare - otherwise
we can't code generate existing bitcode without a string equality data layout.
This reverts commit r294702.
llvm-svn: 294709
For other platforms we should find out what they need and likely
make the same change, however, a smaller additional change is easier
for platforms we know have it specified in the ABI. As part of this
rewrite some of the handling in the backends for data layout and update
a bunch of testcases.
Based on a patch by Simonas Kazlauskas!
llvm-svn: 294702
This requires that we communicate to X86InstrInfo::optimizeCompareInstr
that the second operand is neither a register nor an immediate. The way we
do that is by setting CmpMask to zero.
Note that there were already instructions where the second operand was not a
register nor an immediate, namely X86::SUB*rm, so also set CmpMask to zero
for those instructions. This seems like a latent bug, but I was unable to
trigger it.
Differential Revision: https://reviews.llvm.org/D28621
llvm-svn: 294634
In combineOrCmpEqZeroToCtlzSrl, replace "getConstantOperand == 0" by "isNullConstant" to account for floating point constants.
Differential Revision: https://reviews.llvm.org/D29756
llvm-svn: 294588
LowerBuildVectorv16i8/LowerBuildVectorv8i16 insert values into a UNDEF vector if the build vector doesn't contain any zero elements, resulting in register dependencies with a previous use of the register.
This patch attempts to break the register dependency by either always zeroing the vector before hand or (if we're inserting to the 0'th element) by using VZEXT_MOVL(SCALAR_TO_VECTOR(i32 AEXT(Elt))) which lowers to (V)MOVD and performs a similar function. Additionally (V)MOVD is a shorter instruction than PINSRB/PINSRW. We already do something similar for SSE41 PINSRD.
On pre-SSE41 LowerBuildVectorv16i8 we go a little further and use VZEXT_MOVL(SCALAR_TO_VECTOR(i32 ZEXT(Elt))) if the build vector contains zeros to avoid the vector zeroing at the cost of a scalar zero extension, which can probably be brought over to the other cases in a future patch in some cases (load folding etc.)
Differential Revision: https://reviews.llvm.org/D29720
llvm-svn: 294581
We only implemented it for one of the 3 HLE instructions and that instruction is also under the RTM flag. Clang only implements the RTM flag from its command line.
llvm-svn: 294562
This patch does the following.
1. Adds an Intrinsic int_x86_clzero which works with __builtin_ia32_clzero
2. Identifies clzero feature using cpuid info. (Function:8000_0008, Checks if EBX[0]=1)
3. Adds the clzero feature under znver1 architecture.
4. The custom inserter is added in Lowering.
5. A testcase is added to check the intrinsic.
6. The clzero instruction is added to assembler test.
Patch by Ganesh Gopalasubramanian with a couple formatting tweaks, a disassembler test, and using update_llc_test.py from me.
Differential revision: https://reviews.llvm.org/D29385
llvm-svn: 294558
They are currently modelled incorrectly (as calls, which clobber
registers, confusing e.g. Machine Copy Propagation).
Reverting until we figure out the proper solution.
llvm-svn: 294348
Summary:
This change allows usage of store instruction for implicit null check.
Memory Aliasing Analisys is not used and change conservatively supposes
that any store and load may access the same memory. As a result
re-ordering of store-store, store-load and load-store is prohibited.
Patch by Serguei Katkov!
Reviewers: reames, sanjoy
Reviewed By: sanjoy
Subscribers: atrick, llvm-commits
Differential Revision: https://reviews.llvm.org/D29400
llvm-svn: 294338
vXi8/vXi64 vector shifts are often shifted as vYi16/vYi32 types but we weren't always remembering to bitcast the input.
Tested with a new assert as we don't currently manipulate these shifts enough for test cases to catch them.
llvm-svn: 294308
This includes unmasked forms of variable shift and shifting by the lower element of a register.
Still need to do shift by immediate which was not foldable prior to avx512 and all the masked forms.
llvm-svn: 294285
Currently we only combine shuffle nodes if they have a single user to prevent us from causing code bloat by splitting the shuffles into several different combines.
We don't take into account that in some cases we will already have combined all the users during recursively calling up the shuffle tree.
This patch keeps a list of all the shuffle nodes that have been combined so far and permits combining of further shuffle nodes if all its users are in that list.
Differential Revision: https://reviews.llvm.org/D29399
llvm-svn: 294183
Similar to what we already do for zero elt insertion, we can quickly rematerialize 'allbits' vectors so to avoid a unnecessary gpr value and insertion into a vector
llvm-svn: 294162
Summary:
Make this interface reusable similarly to std::call_once and std::once_flag interface.
This makes porting LLDB to NetBSD easier as there was in the original approach a portable way to specify a non-static once_flag. With this change translating std::once_flag to llvm::once_flag is mechanical.
Sponsored by <The NetBSD Foundation>
Reviewers: mehdi_amini, labath, joerg
Reviewed By: mehdi_amini
Subscribers: emaste, clayborg
Differential Revision: https://reviews.llvm.org/D29566
llvm-svn: 294143
Similar was already done for several other shuffles in this function.
The test changes are because the old code used explicity zeroing for elements that could have been undef.
While I was here I also changed other shuffle vectors in the same function to use the same input twice instead of creating UNDEF nodes. getVectorShuffle can create the UNDEF for us.
llvm-svn: 294130
On one test this seems to have given more chance for DAG combine to do other INSERT_SUBVECTOR/EXTRACT_SUBVECTOR combines before the BLENDI was created. Looks like we can still improve more by teaching DAG combine to optimize INSERT_SUBVECTOR/EXTRACT_SUBVECTOR with BLENDI.
llvm-svn: 293944
Merging Load-add-store pattern into a increment op previously dropped
the load's chain from the instructions dependence if the store is
chained to a TokenFactor.
llvm-svn: 293892
This is a first attempt at using the MOVMSK instructions to replace all_of/any_of reduction patterns (i.e. an and/or + shuffle chain).
So far this only matches patterns where we are reducing an all/none bits source vector (i.e. a comparison result) but we should be able to expand on this in conjunction with improvements to 'bool vector' handling both in the x86 backend as well as the vectorizers etc.
Differential Revision: https://reviews.llvm.org/D28810
llvm-svn: 293880
This moves creation of SUBV_BROADCAST and merging of adjacent loads that are being inserted together.
This is a step towards removing legalizing of INSERT_SUBVECTOR except for vXi1 cases.
llvm-svn: 293872
For SSE we use fp because of the smaller encoding, but that doesn't apply to AVX. So just do the natural thing so we don't have to explain why we aren't. We can't do this for 256-bit loads/stores since integer loads and stores aren't available in AVX1 so we need fallback patterns since the integer types are legal.
This doesn't affect any tests because execution domain fixing freely converts the instructions anyway. Honestly, we could probably rely on it for the SSE size optimization too.
llvm-svn: 293743
This patch moves the class for scheduling adjacent instructions,
MacroFusion, to the target.
In AArch64, it also expands the fusion to all instructions pairs in a
scheduling block, beyond just among the predecessors of the branch at the
end.
Differential revision: https://reviews.llvm.org/D28489
llvm-svn: 293737
@ABS8 can be applied to symbols which appear as immediate operands to
instructions that have a 8-bit immediate form for that operand. It causes
the assembler to use the 8-bit form and an 8-bit relocation (e.g. R_386_8
or R_X86_64_8) for the symbol.
Differential Revision: https://reviews.llvm.org/D28688
llvm-svn: 293667
Also add the ability to recognise PINSR(Vex, 0, Idx).
Targets shuffle combines won't replace multiple insertions with a bit mask until a depth of 3 or more, so we avoid codesize bloat.
The unnecessary vpblendw in clearupper8xi16a will be fixed in an upcoming patch.
llvm-svn: 293627
combineX86ShufflesRecursively can still only handle a maximum of 2 shuffle inputs but everything before it now supports any number of shuffle inputs.
This will be necessary for combining OR(SHUFFLE, SHUFFLE) patterns.
llvm-svn: 293560
Previously this test case fired an assertion in getNode because we tried to create an insert_subvector with both input types the same size and the index pointing to half the vector width.
llvm-svn: 293446
Replaces an xor+movd/movq with an xorps which will be shorter in codesize, avoid an int-fpu transfer, allow modern cores to fast path the result during decode and helps other combines recognise an all-zero vector.
The only reason I can think of that we'd want to keep scalar_to_vector in this case is to help recognise the upper elts are undef but this doesn't seem to be a problem.
Differential Revision: https://reviews.llvm.org/D29097
llvm-svn: 293438
PACKUSWB converts Signed word to Unsigned byte, (the same about DW) and it can't be used for umin+truncate pattern.
AVX-512 VPMOVUS* instructions fit the pattern since they convert Unsigned to Unsigned.
See https://llvm.org/bugs/show_bug.cgi?id=31773
Differential Revision: https://reviews.llvm.org/D29196
llvm-svn: 293431
We had various variants of defining dump() functions in LLVM. Normalize
them (this should just consistently implement the things discussed in
http://lists.llvm.org/pipermail/cfe-dev/2014-January/034323.html
For reference:
- Public headers should just declare the dump() method but not use
LLVM_DUMP_METHOD or #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
- The definition of a dump method should look like this:
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MyClass::dump() {
// print stuff to dbgs()...
}
#endif
llvm-svn: 293359
Summary: Small change to get the FREEP instruction to decode properly.
Reviewers: craig.topper
Reviewed By: craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D29193
llvm-svn: 293314
Pulled out code that removed unused inputs from a target shuffle mask into a helper function to allow it to be reused in a future commit.
llvm-svn: 293175
Refactoring to remove duplications of this method.
New method getOperandsScalarizationOverhead() that looks at the present unique
operands and add extract costs for them. Old behaviour was to just add extract
costs for one operand of the type always, which still happens in
getArithmeticInstrCost() if no operands are provided by the caller.
This is a good start of improving on this, but there are more places
that can be improved by using getOperandsScalarizationOverhead().
Review: Hal Finkel
https://reviews.llvm.org/D29017
llvm-svn: 293155
Enable the next form (intel style):
"mov <reg64>, <largeImm>"
which is should be available,
where <largeImm> stands for immediates which exceed the range of a singed 32bit integer
Differential Revision: https://reviews.llvm.org/D28988
llvm-svn: 293030
As discussed on D28219 - it is profitable to combine trunc(binop (s/zext(x), s/zext(y)) to binop(trunc(s/zext(x)), trunc(s/zext(y))) assuming the trunc(ext()) will simplify further
llvm-svn: 292493
Summary:
Currently we expand and scalarize these operations, but I think we should be able to implement ADD/SUB with KXOR and MUL with KAND.
We already do this for scalar i1 operations so I just extended it to vectors of i1.
Reviewers: zvi, delena
Reviewed By: delena
Subscribers: guyblank, llvm-commits
Differential Revision: https://reviews.llvm.org/D28888
llvm-svn: 292474
r291670 doesn't crash on the original testcase from PR31589,
but it crashes on a slightly more complex one.
PR31589 has the new reproducer.
llvm-svn: 292444
This patch improves the mul instruction combine function (combineMul)
by adding new layer of logic.
In this patch, we are adding the ability to fold (mul x, -((1 << c) -1))
or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective.
Differential Revision: https://reviews.llvm.org/D28232
llvm-svn: 292358
This patch fixes bugzilla 31576 (https://llvm.org/bugs/show_bug.cgi?id=31576).
"data32" instruction prefix was not defined in the llvm.
An exception had to be added to the X86 tablegen and AsmPrinter because both "data16" and "data32" are encoded to 0x66 (but in different modes).
Differential Revision: https://reviews.llvm.org/D28468
llvm-svn: 292352
Even with the fix from r291630, this still causes problems. I get
widespread assertion failures in the Swift runtime's WeakRefCount::increment()
function. I sent a reduced testcase in reply to the commit.
llvm-svn: 292242
We were frequently checking for a list of types and the different types
conveyed no real information. So lump them together explicitly.
llvm-svn: 292095
These all involve bitcasts around the memory operands. This isn't
something we normally do for isel patterns. I suspect DAG combine should
convert the load type making this unnecessary.
llvm-svn: 292050
VPMACSDQH/VPMACSDQL act as VPADDQ( VPMULDQ( x, y ), z ) - multiply+extending either the odd/even 4i32 input elements and adding to v2i64 accumulator
llvm-svn: 292020
Isel now selects masked move instructions for vselect instead of blendm. But sometimes it beneficial to register allocation to remove the tied register constraint by using blendm instructions.
This also picks up cases where the masked move was created due to a masked load intrinsic.
Differential Revision: https://reviews.llvm.org/D28454
llvm-svn: 292005
We'll now expand AVX512_128_SET0 to an EVEX VXORD if VLX available. Or if its not, but register allocation has selected a non-extended register we will use VEX VXORPS. And if its an extended register without VLX we'll use a 512-bit XOR. Do the same for AVX512_FsFLD0SS/SD.
This makes it possible for the register allocator to have all 32 registers available to work with.
llvm-svn: 292004
Use v8i64 variable ASHR instructions if we don't have VLX.
This is a reduced version of D28537 that just adds support for variable shifts - I'll continue with that patch (for just constant/uniform shifts) once I've fixed the type legalization issue in avx512-cvt.ll.
Differential Revision: https://reviews.llvm.org/D28604
llvm-svn: 291901
Rename from addOperand to just add, to match the other method that has been
added to MachineInstrBuilder for adding more than just 1 operand.
See https://reviews.llvm.org/D28057 for the whole discussion.
Differential Revision: https://reviews.llvm.org/D28556
llvm-svn: 291891
Some shuffles can be lowered to blend mask instruction (VPBLENDMB/VPBLENDMW/VPBLENDMD/VPBLENDMQ) .
In this patch, I added new pattern match for this case.
Reviewers:
1. craig.topper
2. guyblank
3. RKSimon
4. igorb
Differential Revision: https://reviews.llvm.org/D28483
llvm-svn: 291888
These aren't the most interesting set of blendm instructions as the unmasked version isn't useful. We were also missing the B and W forms. I'll add the masked versions of all sizes in a future patch.
llvm-svn: 291885
Emit SHRQ/SHLQ instead of ANDQ with a 64 bit constant mask if the result
is unused and the mask has only higher/lower bits set. For example, with
this patch LLVM emits
shrq $41, %rdi
je
instead of
movabsq $0xFFFFFE0000000000, %rcx
testq %rcx, %rdi
je
This reduces number of instructions, code size and register pressure.
The transformation is applied only for cases where the mask cannot be
encoded as an immediate value within TESTQ instruction.
Differential Revision: https://reviews.llvm.org/D28198
llvm-svn: 291806
64-bit integer division in Intel CPUs is extremely slow, much slower
than 32-bit division. On the other hand, 8-bit and 16-bit divisions
aren't any faster. The only important exception is Atom where DIV8
is fastest. Because of that, the patch
1) Enables bypassing of 64-bit division for Atom, Silvermont and
all big cores.
2) Modifies 64-bit bypassing to use 32-bit division instead of
16-bit one. This doesn't make the shorter division slower but
increases chances of taking it. Moreover, it's much more likely
to prove at compile-time that a value fits 32 bits and doesn't
require a run-time check (e.g. zext i32 to i64).
Differential Revision: https://reviews.llvm.org/D28196
llvm-svn: 291800
r289653 added a case where `vselect <cond> <vector1> <all-zeros>`
is transformed to:
`vselect xor(cond, DAG.getConstant(1, DL, CondVT) <all-zeros> <vector1>`
This was not aimed to catch cases where Cond is not a vXi1
mask but it does. Moreover, when Cond type is VxiN (N > 1)
then xor(cond, DAG.getConstant(1, DL, CondVT) != NOT(cond).
This patch changes the above to xor with allones, and avoids
entering the case for non-mask Conds.
llvm-svn: 291745
DAG patterns optimization: truncate + unsigned saturation supported by VPMOVUS* instructions in AVX-512.
And VPACKUS* instructions on SEE* targets.
Differential Revision: https://reviews.llvm.org/D28216
llvm-svn: 291670
The code emiited by Clang's intrinsics for (v)cvtsi2ss, (v)cvtsi2sd,
(v)cvtsd2ss and (v)cvtss2sd is lowered to a code sequence that includes
redundant (v)movss/(v)movsd instructions. This patch adds patterns for
optimizing these sequences.
Differential revision: https://reviews.llvm.org/D28455
llvm-svn: 291660
updated instructions:
pmulld, pmullw, pmulhw, mulsd, mulps, mulpd, divss, divps, divsd, divpd, addpd and subpd.
special optimization case which replaces pmulld with pmullw\pmulhw\pshuf seq.
In case if the real operands bitwidth <= 16.
Differential Revision: https://reviews.llvm.org/D28104
llvm-svn: 291657
This was reverted because it would miscompile code where the cmp had
multiple uses. That was due to a deficiency in the existing code, which
was fixed in r291630 (see the PR for details).
This re-commit includes an extra test for the kind of code that got
miscompiled: @test_sub_1_setcc_jcc.
llvm-svn: 291640
We would miscompile the following:
void g(int);
int f(volatile long long *p) {
bool b = __atomic_fetch_add(p, 1, __ATOMIC_SEQ_CST) < 0;
g(b ? 12 : 34);
return b ? 56 : 78;
}
into
pushq %rax
lock incq (%rdi)
movl $12, %eax
movl $34, %edi
cmovlel %eax, %edi
callq g(int)
testq %rax, %rax <---- Bad.
movl $56, %ecx
movl $78, %eax
cmovsl %ecx, %eax
popq %rcx
retq
because the code failed to take into account that the cmp has multiple
uses, replaced one of them, and left the other one comparing garbage.
llvm-svn: 291630
This patch fix PR31351: https://llvm.org/bugs/show_bug.cgi?id=31351
1. This patch adds new type of shuffle lowering
2. We can use the expand instruction, When the shuffle pattern is as following:
{ 0*a[0]0*a[1]...0*a[n] , n >=0 where a[] elements in a ascending order}.
Reviewers: 1. igorb
2. guyblank
3. craig.topper
4. RKSimon
Differential Revision: https://reviews.llvm.org/D28352
llvm-svn: 291584
Summary:
This patch enables the following
1. AMD family 17h architecture using "znver1" tune flag (-march, -mcpu).
2. ISAs that are enabled for "znver1" architecture.
3. Checks ADX isa from cpuid to identify "znver1" flag when -march=native is used.
4. ISAs FMA4, XOP are disabled as they are dropped from amdfam17.
5. For the time being, it uses the btver2 scheduler model.
6. Test file is updated to check this flag.
This item is linked to clang review item https://reviews.llvm.org/D28018
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, RKSimon, ashutosh.nema, llvm-commits
Differential Revision: https://reviews.llvm.org/D28017
llvm-svn: 291543
Use the existing AVX2 v8i16 vector shift lowering for v16i8 (extending to v16i32) on AVX512 targets and v32i8 (extending to v32i16) on AVX512BW targets.
Cost model updates to follow.
llvm-svn: 291451
Use the existing AVX2 v8i16 vector shift lowering for v16i16 on AVX512 targets (AVX512BW will have already have lowered with vpsravw).
Cost model updates to follow.
llvm-svn: 291445
I noticed this problem as part of the ongoing attempt to canonicalize min/max ops in IR.
The debug output shows nodes like this:
t4: i32 = xor t2, Constant:i32<-1>
t21: i8 = setcc t4, Constant:i32<0>, setlt:ch
t14: i32 = select t21, t4, Constant:i32<-1>
And because the select is holding onto the t4 (xor) node while EmitTest creates a new
x86-specific xor node, the lowering results in:
t4: i32 = xor t2, Constant:i32<-1>
t25: i32,i32 = X86ISD::XOR t2, Constant:i32<-1>
t28: i32,glue = X86ISD::CMOV Constant:i32<-1>, t4, Constant:i8<15>, t25:1
Differential Revision: https://reviews.llvm.org/D28374
llvm-svn: 291392
The 'fast' costs should only work for shifts by uniform constants (uniform non-constant are lowered using the slow default implementation).
Logical shifts were not taking into account that we must mask the psrlw result, so the costs needed to be doubled.
Added missing AVX2/AVX512BW costs as well.
llvm-svn: 291391
We should probably teach the two address instruction pass to turn masked moves into BLENDM when its beneficial to the register allocator.
llvm-svn: 291371
All but (v2f64 broadcast f64) are handled with VBROADCAST instructions. The v2f64 version can be handled with VMOVDDUP.
We may want to consider converting to BLENDM instructions in the two address instruction pass if its beneficial to register allocation.
llvm-svn: 291369
Summary:
For instructions such as PSLLW/PSLLD/PSLLQ a variable shift amount may be passed in an XMM register.
The lower 64-bits of the register are evaluated to determine the shift amount.
This patch improves the construction of the vector containing the shift amount.
Reviewers: craig.topper, delena, RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28353
llvm-svn: 291120
This code seems to be target dependent which may not be the same for all targets.
Passed the decision whether the given stride is complex or not to the target by sending stride information via SCEV to getAddressComputationCost instead of 'IsComplex'.
Specifically at X86 targets we dont see any significant address computation cost in case of the strided access in general.
Differential Revision: https://reviews.llvm.org/D27518
llvm-svn: 291106
Summary:
In mergeSPUpdates, debug values need to be ignored when getting the
previous element, otherwise debug data could have an impact on codegen.
In eliminateCallFramePseudoInstr, debug values after the erased element
could have an impact on codegen and should be skipped.
Closes PR31319 (https://llvm.org/bugs/show_bug.cgi?id=31319)
Reviewers: aprantl, MatzeB, mkuper
Subscribers: gbedwell, llvm-commits
Differential Revision: https://reviews.llvm.org/D27688
llvm-svn: 290955
Replacing the memory operand in the intrinsic versions of the comis/ucomis instrucions from f128mem to ssmem/sdmem accordingly.
Differential Revision: https://reviews.llvm.org/D28138
llvm-svn: 290948
In some cases its more efficient to combine TRUNC( BINOP( X, Y ) ) --> BINOP( TRUNC( X ), TRUNC( Y ) ) if the binop is legal for the truncated types.
This is true for vector integer multiplication (especially vXi64), as well as ADD/AND/XOR/OR in cases where we only need to truncate one of the inputs at runtime (e.g. a duplicated input or an one use constant we can fold).
Further work could be done here - scalar cases (especially i64) could often benefit (if we avoid partial registers etc.), other opcodes, and better analysis of when truncating the inputs reduces costs.
I have considered implementing this for all targets within the DAGCombiner but wasn't sure we could devise a suitable cost model system that would give us the range we need.
Differential Revision: https://reviews.llvm.org/D28219
llvm-svn: 290947
Summary:
No need to have this per-architecture. While there, unify 32-bit ARM's
behaviour with what changed elsewhere and start function names lowercase
as per the coding standards. Individual entry emission code goes to the
entry's own class.
Fully tested on amd64, cross-builds on both ARMs and PowerPC.
Reviewers: dberris
Subscribers: aemerson, llvm-commits
Differential Revision: https://reviews.llvm.org/D28209
llvm-svn: 290858
X86 target does not provide any target specific cost calculation for interleave patterns.It uses the common target-independent calculation, which gives very high numbers. As a result, the scalar version is chosen in many cases. The situation on AVX-512 is even worse, since we have 3-src shuffles that significantly reduce the cost.
In this patch I calculate the cost on AVX-512. It will allow to compare interleave pattern with gather/scatter and choose a better solution (PR31426).
* Shiffle-broadcast cost will be changed in Simon's upcoming patch.
Differential Revision: https://reviews.llvm.org/D28118
llvm-svn: 290810
This reverts commit r290694. It broke sanitizer tests on Win64. I'll
probably bring this back, but the jump tables will just live in .text
like they do for MSVC.
llvm-svn: 290714
Summary:
We were already using 32-bit jump table entries, but this was a
consequence of the default PIC model on Win64, and not an intentional
design decision. This patch ensures that we always use 32-bit label
difference jump table entries on Win64 regardless of the PIC model. This
is a good idea because it saves executable size and object file size.
Moving the jump tables to .rdata cleans up the disassembled object code
and reduces the available ROP targets, but it requires adding one more
RIP-relative lea to the code. COFF doesn't have relocations to express
the difference between two arbitrary symbols, so we can't use the jump
table label in the label difference like we do elsewhere.
Fixes PR31488
Reviewers: majnemer, compnerd
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28141
llvm-svn: 290694
There are cases of AVX-512 instructions that have two possible encodings. This is the case with instructions that use vector registers with low indexes of 0 - 15 and do not use the zmm registers or the mask k registers.
The EVEX encoding prefix requires 4 bytes whereas the VEX prefix can take only up to 3 bytes. Consequently, using the VEX encoding for these instructions results in a code size reduction of ~2 bytes even though it is compiled with the AVX-512 features enabled.
Reviewers: Craig Topper, Zvi Rackoover, Elena Demikhovsky
Differential Revision: https://reviews.llvm.org/D27901
llvm-svn: 290663
The 128 and 256 bit masked intrinsics are currently unused by clang. The sse and avx2 unmasked intrinsics are used instead. The new 512-bit intrinsic will be used to do the same. Then all masked versions will removed and autoupgraded.
llvm-svn: 290573
Summary:
In mergeSPUpdates, debug values need to be ignored when getting the
previous element, otherwise debug data could have an impact on codegen.
In eliminateCallFramePseudoInstr, debug values after the erased element
could have an impact on codegen and should be skipped.
Closes PR31319 (https://llvm.org/bugs/show_bug.cgi?id=31319)
Reviewers: mkuper, MatzeB, aprantl
Subscribers: gbedwell, llvm-commits
Differential Revision: https://reviews.llvm.org/D27688
llvm-svn: 290423
This is for splitMergedValStore in DAG Combine to share the target query interface
with similar logic in CodeGenPrepare.
Differential Revision: https://reviews.llvm.org/D24707
llvm-svn: 290363
Replacing the memory operand in the ymm version of VPMADDWD from i128mem to i256mem.
Differential Revision: https://reviews.llvm.org/D28024
llvm-svn: 290333
I added API for creation a target specific memory node in DAG. Today, all memory nodes are common for all targets and their constructors are located in SelectionDAG.cpp.
There are some cases in X86 where we need to create a special node - truncation-with-saturation store, float-to-half-store.
In the current patch I added truncation-with-saturation nodes and I'm using them for intrinsics. In the future I plan to implement DAG lowering for truncation-with-saturation pattern.
Differential Revision: https://reviews.llvm.org/D27899
llvm-svn: 290250
Oren Ben Simhon