Optimized lowering of BITCAST node. The BITCAST node can be replaced with COPY_TO_REG instead of KMOV.
It allows to suppress two opposite BITCAST operations and avoid redundant "movs".
Differential Revision: https://reviews.llvm.org/D23247
llvm-svn: 277958
This is a new test that should explore a current suboptimal sequence in passing values between cmp and kor intrinsics.
The code will be optimized in an upcoming patch.
Submitted bug here:
https://llvm.org/bugs/show_bug.cgi?id=28839
llvm-svn: 277954
Assuming SSE2 is available then we can safely commute between these, removing some unnecessary register moves and improving memory folding opportunities.
VEX encoded versions don't benefit so I haven't added support to them.
llvm-svn: 277930
On modern Intel processors hardware SQRT in many cases is faster than RSQRT
followed by Newton-Raphson refinement. The patch introduces a simple heuristic
to choose between hardware SQRT instruction and Newton-Raphson software
estimation.
The patch treats scalars and vectors differently. The heuristic is that for
scalars the compiler should optimize for latency while for vectors it should
optimize for throughput. It is based on the assumption that throughput bound
code is likely to be vectorized.
Basically, the patch disables scalar NR for big cores and disables NR completely
for Skylake. Firstly, scalar SQRT has shorter latency than NR code in big cores.
Secondly, vector SQRT has been greatly improved in Skylake and has better
throughput compared to NR.
Differential Revision: https://reviews.llvm.org/D21379
llvm-svn: 277725
This should ensure that we can atomically write two bytes (on top of the
retq and the one past it) and have those two bytes not straddle cache
lines.
We also move the label past the alignment instruction so that we can refer
to the actual first instruction, as opposed to potential padding before the
aligned instruction.
Update the tests to allow us to reflect the new order of assembly.
Reviewers: rSerge, echristo, majnemer
Subscribers: llvm-commits, mehdi_amini
Differential Revision: https://reviews.llvm.org/D23101
llvm-svn: 277701
We currently only support combining target shuffles that consist of a single source input (plus elements known to be undef/zero).
This patch generalizes the recursive combining of the target shuffle to collect all the inputs, merging any duplicates along the way, into a full set of src ops and its shuffle mask.
We uncover a number of cases where we have failed to combine a unary shuffle because the input has been duplicated and separated during lowering.
This will allow us to combine to 2-input shuffles in a future patch.
Differential Revision: https://reviews.llvm.org/D22859
llvm-svn: 277631
Summary:
We also add a test to show what currently happens when we create a
section per function and emit an xray_instr_map. This illustrates the
relationship (or lack thereof) between the per-function section and the
xray_instr_map section.
We also change the code generation slightly so that we don't always
create group sections, but rather only do so if a function where the
table is associated with is in a group.
Also in this change:
- Remove the "merge" flag on the xray_instr_map section.
- Test that we're generating the right table for comdat and non-comdat functions.
Reviewers: echristo, majnemer
Subscribers: llvm-commits, mehdi_amini
Differential Revision: https://reviews.llvm.org/D23104
llvm-svn: 277580
We used to combine "sext(setcc x, y, cc) -> (select (setcc x, y, cc), -1, 0)"
Instead, we should combine to (select (setcc x, y, cc), T, 0) where the value
of T is 1 or -1, depending on the type of the setcc, and getBooleanContents()
for the type if it is not i1.
This fixes PR28504.
llvm-svn: 277371
As discussed on PR14593, this patch adds support for lowering to SHLD/SHRD from the patterns generated by DAGTypeLegalizer::ExpandShiftWithKnownAmountBit.
Differential Revision: https://reviews.llvm.org/D23000
llvm-svn: 277299
Up until now, we only had code to match PSADBW patterns that look like what
comes out of the loop vectorizer - a partial reduction inside the loop body
that gets fed into a horizontal operation in a different basic block.
This adds support for straight-line patterns, like those generated by the
SLP vectorizer.
Differential Revision: https://reviews.llvm.org/D22889
llvm-svn: 277219
Support for lowering to VBROADCASTF128 etc. in D22460 was not correctly ensuring that the only users of the 128-bit vector load were the insertions of the vector into the lower/upper subvectors.
llvm-svn: 277214
Patch by Sunita Marathe
Third try, now following fixes to MSan to handle mempcy in such a way that this commit won't break the MSan buildbots. (Thanks, Evegenii!)
llvm-svn: 277189
The following pattern was being layed out poorly:
A
/ \
B C
/ \ / \
D E ? (Doesn't matter)
Where A->B is far more likely than A->C, and prob(B->D) = prob(B->E)
The current algorithm gives:
A,B,C,E (D goes on worklist)
It does this even if C has a frequency count of 0. This patch
adjusts the layout calculation so that if freq(B->E) >> freq(C->E)
then we go ahead and layout E rather than C. Fallthrough half the time
is better than fallthrough never, or fallthrough very rarely. The
resulting layout is:
A,B,E, (C and D are in a worklist)
llvm-svn: 277187
We currently default to using either generic shuffles or MASK+PACKUS/PACKSS to truncate all integer vectors. For vector comparisons, we know that the result will be either all or zero bits in every element, which can be efficiently truncated by directly using PACKSS to repeatedly halve the size of each element.
Due to the limited input values (-1 or 0) we don't need to account for vector element size, so for simplicity we just use the PACKSS(vXi16,vXi16) implementation in all cases. Additionally for AVX2 PACKSS of 256bit data we must perform a PERMQ shuffle to reorder the data into the correct order. I did investigate performing a single shuffle after all the PACKSS calls but the need to cross 128bit lanes makes this difficult to achieve efficiently.
We avoid performing this on AVX512 as it should have better alternative truncation instructions.
Differential Revision: https://reviews.llvm.org/D22814
llvm-svn: 277132
I'm not convinced the patterns for the rm_Int was correct anyway. It had a tied source that should't exist for the unmasked version. The load form of MOVSS always zeros the most significant bits. I've left the patterns off the masked load instructions as I'm not sure what the correct pattern should be and we don't have any tests currently. Nor do we implement masked scalar load intrinsics in clang currently.
llvm-svn: 277098
Using getZExtValue() will assert if the value doesn't fit into uint64_t - SHL was already doing this, I've just updated ASHR/LSHR to match
As mentioned on D22726
llvm-svn: 276855
In an instruction like:
CFI_INSTRUCTION .cfi_def_cfa ...
we can drop the '.cfi_' prefix since that should be obvious by the
context:
CFI_INSTRUCTION def_cfa ...
While being a terser and cleaner syntax this also prepares to dropping
support for identifiers starting with a dot character so we can use it
for expressions.
Differential Revision: http://reviews.llvm.org/D22388
llvm-svn: 276785
Fixed typo in the intrinsic definitions of (v)cvtsd2ss with memory folding.
This was only unearthed when rL276102 started using the intrinsic again.....
llvm-svn: 276740
This places the 132/213/231 form number in front of the SS/SD/PS/PD. Move the Y for 256-bit versions to be after the PS/PD. Change the AVX512 scalar forms to include a Z in the their name. This new format should be consistent with the general naming of instructions.
llvm-svn: 276559
An extension of D19978, this patch replaces the default BITREVERSE evaluation of individual bit masks+shifts with block mask+shifts when we have integer elements of power-of-2 bits in size.
After calling BSWAP to reverse the order of the constituent bytes (which typically follows a similar approach), every neighbouring 4-bits, 2-bits and finally 1-bit pairs are masked off and swapped over with shifts.
In doing so we can significantly reduce the number of operations required.
Differential Revision: https://reviews.llvm.org/D21578
llvm-svn: 276432
As reported on PR26235, we don't currently make use of the VBROADCASTF128/VBROADCASTI128 instructions (or the AVX512 equivalents) to load+splat a 128-bit vector to both lanes of a 256-bit vector.
This patch enables lowering from subvector insertion/concatenation patterns and auto-upgrades the llvm.x86.avx.vbroadcastf128.pd.256 / llvm.x86.avx.vbroadcastf128.ps.256 intrinsics to match.
We could possibly investigate using VBROADCASTF128/VBROADCASTI128 to load repeated constants as well (similar to how we already do for scalar broadcasts).
Reapplied with fix for PR28657 - removed intrinsic definitions (clang companion patch to be be submitted shortly).
Differential Revision: https://reviews.llvm.org/D22460
llvm-svn: 276416
This variant is (as documented in the TD) for disassembler use only, and should
not be used in patterns - it is longer, and is broken on 64-bit.
llvm-svn: 276347
Under normal circumstances we prefer the higher performance MOVD to extract the 0'th element of a v8i16 vector instead of PEXTRW.
But as detailed on PR27265, this prevents the SSE41 implementation of PEXTRW from folding the store of the 0'th element. Additionally it prevents us from making use of the fact that the (SSE2) reg-reg version of PEXTRW implicitly zero-extends the i16 element to the i32/i64 destination register.
This patch only preferentially lowers to MOVD if we will not be zero-extending the extracted i16, nor prevent a store from being folded (on SSSE41).
Fix for PR27265.
Differential Revision: https://reviews.llvm.org/D22509
llvm-svn: 276289
As reported on PR26235, we don't currently make use of the VBROADCASTF128/VBROADCASTI128 instructions (or the AVX512 equivalents) to load+splat a 128-bit vector to both lanes of a 256-bit vector.
This patch enables lowering from subvector insertion/concatenation patterns and auto-upgrades the llvm.x86.avx.vbroadcastf128.pd.256 / llvm.x86.avx.vbroadcastf128.ps.256 intrinsics to match.
We could possibly investigate using VBROADCASTF128/VBROADCASTI128 to load repeated constants as well (similar to how we already do for scalar broadcasts).
Differential Revision: https://reviews.llvm.org/D22460
llvm-svn: 276281
The clearance calculation did not take into account registers defined as outputs or clobbers in inline assembly machine instructions because these register defs are implicit.
Differential Revision: http://reviews.llvm.org/D22580
llvm-svn: 276266
This patch fixes a very subtle bug in regmask calculation. Thanks to zan
jyu Wong <zyfwong@gmail.com> for bringing this to notice.
For example if CL is only clobbered than CH should not be marked
clobbered but CX, RCX and ECX should be mark clobbered. Previously for
each modified register all of its aliases are marked clobbered by
markRegClobbred() in RegUsageInfoCollector.cpp but that is wrong because
when CL is clobbered then MRI::isPhysRegModified() will return true for
CL, CX, ECX, RCX which is correct behavior but then for CX, EXC, RCX we
mark CH also clobbered as CH is aliased to CX,ECX,RCX so
markRegClobbred() is not required because isPhysRegModified already take
cares of proper aliasing register. A very simple test case has been
added to verify this change.
Please find relevant bug report here :
http://llvm.org/PR28567
Patch by Vivek Pandya <vivekvpandya@gmail.com>
Differential Revision: https://reviews.llvm.org/D22400
llvm-svn: 276235
D20859 and D20860 attempted to replace the SSE (V)CVTTPS2DQ and VCVTTPD2DQ truncating conversions with generic IR instead.
It turns out that the behaviour of these intrinsics is different enough from generic IR that this will cause problems, INF/NAN/out of range values are guaranteed to result in a 0x80000000 value - which plays havoc with constant folding which converts them to either zero or UNDEF. This is also an issue with the scalar implementations (which were already generic IR and what I was trying to match).
This patch changes both scalar and packed versions back to using x86-specific builtins.
It also deals with the other scalar conversion cases that are runtime rounding mode dependent and can have similar issues with constant folding.
A companion clang patch is at D22105
Differential Revision: https://reviews.llvm.org/D22106
llvm-svn: 275981
The following condition expression ( a >> n) & 1 is converted to "bt a, n" instruction. It works on all intel targets.
But on AVX-512 it was broken because the expression is modified to (truncate (a >>n) to i1).
I added the new sequence (truncate (a >>n) to i1) to the BT pattern.
Differential Revision: https://reviews.llvm.org/D22354
llvm-svn: 275950
DAGTypeLegalizer::CanSkipSoftenFloatOperand should allow
SELECT op code for x86_64 fp128 type for MME targets,
so SoftenFloatOperand does not abort on SELECT op code.
Differential Revision: http://reviews.llvm.org/D21758
llvm-svn: 275818
Previously, we would expand:
%BL<def> = COPY %DL<kill>, %EBX<imp-use,kill>, %EBX<imp-def>
Into:
%BL<def> = MOV8rr %DL<kill>, %EBX<imp-def>
Dropping the imp-use on the floor.
That confused CriticalAntiDepBreaker, which (correctly) assumes that if an
instruction defs but doesn't use a register, that register is dead immediately
before the instruction - while in this case, the high lanes of EBX can be very
much alive.
This fixes PR28560.
Differential Revision: https://reviews.llvm.org/D22425
llvm-svn: 275634
This mostly just works.
Vectorcall rets are still not supported.
The win64_eh test change is because fast isel doesn't use rsi for temporary
computations, so it doesn't need to be pushed. The test case I'm changing was
originally added to test pushes, but by now there are other test cases in that
file exercising that code path.
https://reviews.llvm.org/D22422
llvm-svn: 275607
The test used to rely on targeting win64 to disable fast isel,
but I'd like to teach fast isel about win64 rets. Change the
test to use varargs to disable fast isel.
llvm-svn: 275568
As discussed on PR28136, lowerShuffleAsRepeatedMaskAndLanePermute was attempting to match repeated masks at the 128-bit level and then permute the resultant lanes at the 128-bit (AVX1) or 64-bit (AVX2) sub-lane level.
This change allows us to create the repeated masks at the sub-lane level (and then concat them together to create a 128-bit repeated mask) and then select which sub-lane to permute. This has no effect on the AVX1 codegen.
Fixes PR28136.
llvm-svn: 275543
This improves the situation discussed in D19228 where we were forcing VPERMPD/VPERMQ where VPERM2F128/VPERM2I128 would have been better.
This was incorrectly reverted in rL275421 during triage of PR28552.
llvm-svn: 275497
Note: I removed the checks after each jump because that's noise, but we apparently
need branches rather than returning i1 to see the bt codegen in some cases.
llvm-svn: 275439
stdcall is callee-pop like thiscall, so the thiscall changes already did most
of the work for this. This change only opts stdcall in and adds tests.
llvm-svn: 275414
This improves the situation discussed in D19228 where we were forcing VPERMPD/VPERMQ where VPERM2F128/VPERM2I128 would have been better.
llvm-svn: 275411
Primarily this is to allow blend with zero instead of having to use vperm2f128, but we can use this in the future to deal with AVX512 cases where we need to keep the original element size to correctly fold masked operations.
llvm-svn: 275406
Summary:
In this patch we implement the following parts of XRay:
- Supporting a function attribute named 'function-instrument' which currently only supports 'xray-always'. We should be able to use this attribute for other instrumentation approaches.
- Supporting a function attribute named 'xray-instruction-threshold' used to determine whether a function is instrumented with a minimum number of instructions (IR instruction counts).
- X86-specific nop sleds as described in the white paper.
- A machine function pass that adds the different instrumentation marker instructions at a very late stage.
- A way of identifying which return opcode is considered "normal" for each architecture.
There are some caveats here:
1) We don't handle PATCHABLE_RET in platforms other than x86_64 yet -- this means if IR used PATCHABLE_RET directly instead of a normal ret, instruction lowering for that platform might do the wrong thing. We think this should be handled at instruction selection time to by default be unpacked for platforms where XRay is not availble yet.
2) The generated section for X86 is different from what is described from the white paper for the sole reason that LLVM allows us to do this neatly. We're taking the opportunity to deviate from the white paper from this perspective to allow us to get richer information from the runtime library.
Reviewers: sanjoy, eugenis, kcc, pcc, echristo, rnk
Subscribers: niravd, majnemer, atrick, rnk, emaste, bmakam, mcrosier, mehdi_amini, llvm-commits
Differential Revision: http://reviews.llvm.org/D19904
llvm-svn: 275367
This happens to make X86CallFrameOptimization in -O0 / FastISel builds as well,
but it's not clear if the pass should run in that setup.
http://reviews.llvm.org/D22314
llvm-svn: 275320
Currently the MIR framework prints all its outputs (errors and actual
representation) on stderr.
This patch fixes that by printing the regular output in the output
specified with -o.
Differential Revision: http://reviews.llvm.org/D22251
llvm-svn: 275314
We know that pcmp produces all-ones/all-zeros bitmasks, so we can use that behavior to avoid unnecessary constant loading.
One could argue that load+and is actually a better solution for some CPUs (Intel big cores) because shifts don't have the
same throughput potential as load+and on those cores, but that should be handled as a CPU-specific later transformation if
it ever comes up. Removing the load is the more general x86 optimization. Note that the uneven usage of vpbroadcast in the
test cases is filed as PR28505:
https://llvm.org/bugs/show_bug.cgi?id=28505
Differential Revision: http://reviews.llvm.org/D22225
llvm-svn: 275276
With r274952 and r275201 in place there are no cases left where a
forward liveness analysis yields different results than a backward one.
So we can remove the forward stepping logic.
Differential Revision: http://reviews.llvm.org/D22083
llvm-svn: 275204
This bug (llvm.org/PR28124) was introduced by r237977, which refactored
the tail call sequence to be generated in two passes instead of one.
Unfortunately, the stack adjustment produced by the first pass was not
recognized by X86FrameLowering::mergeSPUpdates() in all cases, causing
code such as the following, which clobbers the return address, to be
generated:
popl %edi
popl %edi
pushl %eax
jmp tailcallee # TAILCALL
To fix the problem, the entire stack adjustment is performed in
X86ExpandPseudo::ExpandMI() for tail calls.
Patch by Magnus Lång <margnus1@gmail.com>
Differential Revision: http://reviews.llvm.org/D21325
llvm-svn: 275103
It is an optimization pass, and should not run at -O0. Especially since Fast RA
will not do the required register coalescing anyway, so it's a loss even from
the optimization standpoint.
This also works around (but doesn't quite fix) PR28489.
llvm-svn: 275099
An identity COPY like this:
%AL = COPY %AL, %EAX<imp-def>
has no semantic effect, but encodes liveness information: Further users
of %EAX only depend on this instruction even though it does not define
the full register.
Replace the COPY with a KILL instruction in those cases to maintain this
liveness information. (This reverts a small part of r238588 but this
time adds a comment explaining why a KILL instruction is useful).
llvm-svn: 274952
Until we have a better way to extract constants through bitcasted build vectors (and how to handle undefs of partial lanes etc.) at least accept build vectors that are all zeroes.
llvm-svn: 274833
xorl + setcc is generally the preferred sequence due to the partial register
stall setcc + movzbl suffers from. As a bonus, it also encodes one byte smaller.
This fixes PR28146.
The original commit tried inserting an 8bit-subreg into a GR32 (not GR32_ABCD)
which was not appreciated by fast regalloc on 32-bit.
llvm-svn: 274802
These tests don't actually care about the internal opcode number, but have to
be updated whenever we add a new one for GlobalISel. That's bad.
llvm-svn: 274774
xorl + setcc is generally the preferred sequence due to the partial register
stall setcc + movzbl suffers from. As a bonus, it also encodes one byte smaller.
This fixes PR28146.
Differential Revision: http://reviews.llvm.org/D21774
llvm-svn: 274692
The patch removes redundant kmov instructions (not all, we still have a lot of work here) and redundant "and" instructions after "setcc".
I use "AssertZero" marker between X86ISD::SETCC node and "truncate" to eliminate extra "and $1" instruction.
I also changed zext, aext and trunc patterns in the .td file. It allows to remove extra "kmov" instruictions.
This patch fixes https://llvm.org/bugs/show_bug.cgi?id=28173.
Fast ISEL mode is not supported correctly for AVX-512. ICMP/FCMP scalar instruction should return result in k-reg. It will be fixed in one of the next patches. I redirected handling of "cmp" to the DAG builder mode. (The code looks worse in one specific test case, but without this fix the new patch fails).
Differential revision: http://reviews.llvm.org/D21956
llvm-svn: 274613
We can now handle concatenation of each source multiple times. The previous code just checked for each source to appear once in either order.
This also now handles an entire source vector sized piece having undef indices correctly. We now concat with UNDEF instead of using one of the sources. This is responsible for the test case change.
llvm-svn: 274483
After the block placement, if a block ends with a conditional branch, but the
next block is not its successor. The conditional branch should be changed to
unconditional branch. This patch fixes PR28307, PR28297, PR28402.
Differential Revision: http://reviews.llvm.org/D21811
llvm-svn: 274470
This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments.
This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course.
Differential Revision: http://reviews.llvm.org/D21953
llvm-svn: 274459
Its not worth trying to write out tests for all the avx512f builtins yet, just adding tests for lowering of generic IR as we transition to it (shuffles mainly right now).
llvm-svn: 274434
Summary: original test may have different bahavior on different bot, specifically it broke llvm-clang-lld-x86_64-scei-ps4-ubuntu-fast
Reviewers: majnemer
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D21931
llvm-svn: 274368
Summary: The code generation should be independent of the debug info.
Reviewers: zansari, davidxl, mkuper, majnemer
Subscribers: majnemer, llvm-commits
Differential Revision: http://reviews.llvm.org/D21911
llvm-svn: 274357
When lowering two blended PACKUS, we used to disregard the types
of the PACKUS inputs, indiscriminately generating a v16i8 PACKUS.
This leads to non-selectable things like:
(v16i8 (PACKUS (v4i32 v0), (v4i32 v1)))
Instead, check that the PACKUSes have the same type, and use that
as the final result type.
llvm-svn: 274138
Summary: LLVM assumes that large clearance will hide the partial register spill penalty. But in our experiment, 16 clearance is too small. As the inserted XOR is normally fairly cheap, we should have a higher clearance threshold to aggressively insert XORs that is necessary to break partial register dependency.
Reviewers: wmi, davidxl, stoklund, zansari, myatsina, RKSimon, DavidKreitzer, mkuper, joerg, spatel
Subscribers: davidxl, llvm-commits
Differential Revision: http://reviews.llvm.org/D21560
llvm-svn: 274068
This is a resubmittion of 263158 change after fixing the existing problem with intrinsics mangling (see LTO and intrinsics mangling llvm-dev thread for details).
This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.
The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.
Reviewed By: reames
Differential Revision: http://reviews.llvm.org/D17270
llvm-svn: 274043
The original implementation attempted to zero registers using
XOR %foo, %foo. This is problematic because it constitutes a
read-modify-write of a register which might not be defined.
Instead, use MOV32r0 to avoid these problems; expandPostRAPseudo does
the right thing here.
llvm-svn: 274024
AVX1 can only broadcast vectors as floats/doubles, so for 256-bit vectors we insert bitcasts if we are shuffling v8i32/v4i64 types. Unfortunately the presence of these bitcasts prevents the current broadcast lowering code from peeking through cases where we have concatenated / extracted vectors to create the 256-bit vectors.
This patch allows us to peek through bitcasts as long as the number of elements doesn't change (i.e. element bitwidth is the same) so the broadcast index is not affected.
Note this bitcast peek is different from the stage later on which doesn't care about the type and is just trying to find a load node.
As we're being more aggressive with bitcasts, we also need to ensure that the broadcast type is correctly bitcasted
Differential Revision: http://reviews.llvm.org/D21660
llvm-svn: 274013
This patch allows target shuffles to be combined to single input immediate permute instructions - (V)PSHUFD/VPERMILPD/VPERMILPS - allowing more general pattern matching than what we current do and improves the likelihood of memory folding compared to existing patterns which tend to reuse the input in multiple arguments.
Further permute instructions (V)PSHUFLW/(V)PSHUFHW/(V)PERMQ/(V)PERMPD may be added in the future but its proven tricky to create tests cases for them so far. (V)PSHUFLW/(V)PSHUFHW is already handled quite well in combineTargetShuffle so it may be that removing some of that code may allow us to perform more of the combining in one place without duplication.
Differential Revision: http://reviews.llvm.org/D21148
llvm-svn: 273999
This is a resubmittion of 263158 change after fixing the existing problem with intrinsics mangling (see LTO and intrinsics mangling llvm-dev thread for details).
This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace.
The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics.
Reviewed By: reames
Differential Revision: http://reviews.llvm.org/D17270
llvm-svn: 273892
AVX1 can only broadcast vectors as floats/doubles, so for 256-bit vectors we insert bitcasts if we are shuffling v8i32/v4i64 types. Unfortunately the presence of these bitcasts prevents the current broadcast lowering code from peeking through cases where we have concatenated / extracted vectors to create the 256-bit vectors.
This patch allows us to peek through bitcasts as long as the number of elements doesn't change (i.e. element bitwidth is the same) so the broadcast index is not affected.
Note this bitcast peek is different from the stage later on which doesn't care about the type and is just trying to find a load node.
Differential Revision: http://reviews.llvm.org/D21660
llvm-svn: 273848
Tail merge was making the assumption that a layout successor or
predecessor was always a cfg successor/predecessor. Remove that
assumption. Changes to tests are necessary because the errant cfg edges
were preventing optimizations.
llvm-svn: 273700
Craig Topper