| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
| |
This patch adds vaddva selection.
Differential revision: https://reviews.llvm.org/D66410
llvm-svn: 369404
|
| |
|
|
|
|
|
|
|
| |
Latency and throughput of LOCK INC/DEC/NEG/NOT is always 19cy.
Number of uOPs is still 1.
Differential Revision: https://reviews.llvm.org/D66469
llvm-svn: 369388
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
the FDE location
Follow binutils in using RISCV_32_PCREL for the FDE initial location. As
explained in the relevant binutils commit
<https://github.com/riscv/riscv-binutils-gdb/commit/a6cbf936e3dce68114d28cdf60d510a3f78a6d40>,
the ADD/SUB pair of relocations is problematic in the presence of linker
relaxation.
This patch has the same end goal as D64715 but includes test changes and
avoids adding a new global VariantKind to MCExpr.h (preferring
RISCVMCExpr VKs like the rest of the RISC-V backend).
Differential Revision: https://reviews.llvm.org/D66419
llvm-svn: 369375
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
On Jaguar, CMPXCHG has a latency of 11cy, and a maximum throughput of 0.33 IPC.
Throughput is superiorly limited to 0.33 because of the implicit in/out
dependency on register EAX. In the case of repeated non-atomic CMPXCHG with the
same memory location, store-to-load forwarding occurs and values for sequent
loads are quickly forwarded from the store buffer.
Interestingly, the functionality in LLVM that computes the reciprocal throughput
doesn't seem to know about RMW instructions. That functionality only looks at
the "consumed resource cycles" for the throughput computation. It should be
fixed/improved by a future patch. In particular, for RMW instructions, that
logic should also take into account for the write latency of in/out register
operands.
An atomic CMPXCHG has a latency of ~17cy. Throughput is also limited to
~17cy/inst due to cache locking, which prevents other memory uOPs to start
executing before the "lock releasing" store uOP.
CMPXCHG8rr and CMPXCHG8rm are treated specially because they decode to one less
macro opcode. Their latency tend to be the same as the other RR/RM variants. RR
variants are relatively fast 3cy (but still microcoded - 5 macro opcodes).
CMPXCHG8B is 11cy and unfortunately doesn't seem to benefit from store-to-load
forwarding. That means, throughput is clearly limited by the in/out dependency
on GPR registers. The uOP composition is sadly unknown (due to the lack of PMCs
for the Integer pipes). I have reused the same mix of consumed resource from the
other CMPXCHG instructions for CMPXCHG8B too.
LOCK CMPXCHG8B is instead 18cycles.
CMPXCHG16B is 32cycles. Up to 38cycles when the LOCK prefix is specified. Due to
the in/out dependencies, throughput is limited to 1 instruction every 32 (or 38)
cycles dependeing on whether the LOCK prefix is specified or not.
I wouldn't be surprised if the microcode for CMPXCHG16B is similar to 2x
microcode from CMPXCHG8B. So, I have speculatively set the JALU01 consumption to
2x the resource cycles used for CMPXCHG8B.
The two new hasLockPrefix() functions are used by the btver2 scheduling model
check if a MCInst/MachineInst has a LOCK prefix. Calls to hasLockPrefix() have
been encoded in predicates of variant scheduling classes that describe lat/thr
of CMPXCHG.
Differential Revision: https://reviews.llvm.org/D66424
llvm-svn: 369365
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
line flag and all associated code, but leave it enabled by default
Google is reporting performance issues with the new default behavior
and have asked for a way to switch back to the old behavior while we
investigate and make fixes.
I've restored all of the code that had since been removed and added
additional checks of the command flag onto code paths that are
not otherwise guarded by a check of getTypeAction.
I've also modified the cost model tables to hopefully get us back
to the previous costs.
Hopefully we won't need to support this for very long since we
have no test coverage of the old behavior so we can very easily
break it.
llvm-svn: 369332
|
| |
|
|
| |
llvm-svn: 369326
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Overriders may want to modify state in it. AMDGPU wants
to, but has to make its members mutable in order to do so.
Besides, EmitBasicBlockEnd is not const, so why should
Start be?
Patch by Bevin Hansson.
Reviewed By: nickdesaulniers
Differential Revision: https://reviews.llvm.org/D66341
llvm-svn: 369325
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Simplify the API using Optional<> and address comments in
https://reviews.llvm.org/D66165
Reviewers: vitalybuka
Subscribers: hiraditya, llvm-commits, ostannard, pcc
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66317
llvm-svn: 369300
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
MTE provides instructions to update memory tags and data at the same
time. This change makes use of those to generate more compact code for
stack variable tagging + initialization.
We collect memory store and memset instructions following an alloca or a
lifetime.start call, and replace them with the corresponding MTE
intrinsics. Since the intrinsics work on 16-byte aligned chunks, the
stored values are combined as necessary.
Reviewers: pcc, vitalybuka, ostannard
Subscribers: srhines, javed.absar, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66167
llvm-svn: 369297
|
| |
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D66434
llvm-svn: 369292
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
than one undef element. Prioritize shifts over broadcast in lowerV8I16Shuffle.
The motivating case are the changes in vector-reduce-add.ll where
we were doing extra work in the scalar domain instead of shuffling.
There may be some one use check that needs to be looked into there,
but this patch sidesteps the issue by avoiding broadcasts that
aren't really broadcasting.
Differential Revision: https://reviews.llvm.org/D66071
llvm-svn: 369287
|
| |
|
|
| |
llvm-svn: 369266
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
If we have a MI marked with bitcast bits, but without input operands,
PeepholeOptimizer might crash with assert.
eg:
If we apply the changes in PPCInstrVSX.td as in this patch:
[(set v4i32:$XT, (bitconvert (v16i8 immAllOnesV)))]>;
We will get assert in PeepholeOptimizer.
```
llvm-lit llvm-project/llvm/test/CodeGen/PowerPC/build-vector-tests.ll -v
llvm-project/llvm/include/llvm/CodeGen/MachineInstr.h:417: const
llvm::MachineOperand &llvm::MachineInstr::getOperand(unsigned int)
const: Assertion `i < getNumOperands() && "getOperand() out of range!"'
failed.
```
The fix is to abort if we found out of bound access.
Reviewers: qcolombet, MatzeB, hfinkel, arsenm
Reviewed By: qcolombet
Subscribers: wdng, arsenm, steven.zhang, wuzish, nemanjai, hiraditya, kbarton, MaskRay, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65542
llvm-svn: 369261
|
| |
|
|
|
|
|
|
|
|
|
|
| |
The current behavior of shouldForceRelocation forces relocations for the
majority of fixups when relaxation is enabled. This makes sense for
fixups which incorporate symbols but is unnecessary for simple data
fixups where the fixup target is already resolved to an absolute value.
Differential Revision: https://reviews.llvm.org/D63404
Patch by Edward Jones.
llvm-svn: 369257
|
| |
|
|
|
|
|
|
|
| |
This patch adds vecreduce_add and the relevant instruction selection for
vaddv.
Differential revision: https://reviews.llvm.org/D66085
llvm-svn: 369245
|
| |
|
|
|
|
|
|
|
| |
This adds some sext costs for MVE, taken from the length of assembly sequences
that we currently generate.
Differential Revision: https://reviews.llvm.org/D66010
llvm-svn: 369244
|
| |
|
|
|
|
|
|
|
|
| |
on types that don't natively support KSHIFT.
We can support these by widening to a supported type,
then shifting all the way to the left and then
back to the right to ensure that we shift in zeroes.
llvm-svn: 369232
|
| |
|
|
|
|
|
|
|
|
| |
widened vector to the KSHIFT node.
Not sure how to test this as we have tests that exercise this code,
but nothing failed for the types not matching. Since all the k-registers
use equivalent register classes everything just ends up working.
llvm-svn: 369228
|
| |
|
|
|
|
|
|
|
|
|
| |
only relies on undef.
This allows us to widen the type when the KSHIFTR instruction
doesn't exist for the type. If we need to shift in zeroes into
the upper elements we would need more work to guarantee zeroes
when widening.
llvm-svn: 369227
|
| |
|
|
|
|
|
|
|
| |
with V2 as the source and V1 as the zero vector.
Shuffle canonicalization can swap the sources so the zero vector
might be V1 and the subvector that's being padded can be V2.
llvm-svn: 369226
|
| |
|
|
|
|
|
|
|
|
| |
zero vectors followed by one non-zero vector followed by undef vectors.
For such a case we should only need a KSHIFTL, but we were
previously generating a KSHIFTL followed by a KSHIFTR because
we mistakenly believed we need to zero the undef elements.
llvm-svn: 369224
|
| |
|
|
|
|
| |
vXi1 vectors don't need special handling.
llvm-svn: 369222
|
| |
|
|
|
|
|
| |
We can insert the value into a larger legal type and shift that
by the desired amount.
llvm-svn: 369215
|
| |
|
|
| |
llvm-svn: 369213
|
| |
|
|
|
|
|
|
|
|
| |
Add similar functionality to isShuffleEquivalent - if the mask elements don't match, try matching the BUILD_VECTOR scalars instead.
As target shuffles need to handle SM_Sentinel values, this can get a bit tricky, so commit just adds actual mask element index handling - full SM_SentinelZero support will be added when the need arises.
Also, enables support in matchVectorShuffleWithPACK
llvm-svn: 369212
|
| |
|
|
|
|
| |
Simplifies shuffle mask comparisons by just bailing out if the shuffle mask has any out of range values - will make an upcoming patch much simpler.
llvm-svn: 369211
|
| |
|
|
|
|
|
| |
If the instruction is the last in the block, there is no next
instruction but the iteration still needs to look at the new block.
llvm-svn: 369203
|
| |
|
|
|
|
|
|
|
| |
Currently the searchable tables report the number of dwords. These
round to the same number for 3 and 4 component d16
instructions. Change this to report the number of elements so this
isn't ambiguous.
llvm-svn: 369202
|
| |
|
|
|
|
|
|
|
| |
v16i16->v16i8 truncate+store by extending to v16i32 and then emitting a v16i32->v16i8 truncstore.
This prevent us from emitting a separate truncate and a truncating
store instruction.
llvm-svn: 369200
|
| |
|
|
|
|
|
|
| |
for meta instructions.
This reverts r369132 (git commit 19301d75f086caae1a495d267f5d0264b225942d)
llvm-svn: 369186
|
| |
|
|
|
|
|
|
| |
meta instructions.
This reverts r369133 (git commit 2632c677f85cba1ac2aef5d68aaf8af0f5b3c944)
llvm-svn: 369185
|
| |
|
|
|
|
|
|
| |
This relands r369147 with fixes to unit tests.
https://reviews.llvm.org/D65019
llvm-svn: 369173
|
| |
|
|
|
|
| |
types.
llvm-svn: 369172
|
| |
|
|
|
|
|
|
|
|
| |
shuffle using DemandedElts mask (reapplied)
This reverts r368662 (git commit 1a8d790cf5f89c1df718844f13e934e39bef6ef5)
The compile-time regression repro is in https://bugs.llvm.org/show_bug.cgi?id=43024
llvm-svn: 369167
|
| |
|
|
|
|
|
|
|
|
| |
We currently don't use liveness information after this point, but it can
be useful to catch bugs using -verify-machineinstrs, and optimizations
could potentially use this information in the future.
Differential Revision: https://reviews.llvm.org/D66319
llvm-svn: 369162
|
| |
|
|
|
|
|
|
|
|
| |
This was a quick pass through some obvious places. I haven't tried the clang-tidy check.
I also replaced the zeroes in getX86SubSuperRegister with X86::NoRegister which is the real sentinel name.
Differential Revision: https://reviews.llvm.org/D66363
llvm-svn: 369151
|
| |
|
|
|
|
| |
This reverts commit f4cf3b959333f62b7a7b2d7771f7010c9d8da388.
llvm-svn: 369149
|
| |
|
|
|
|
|
|
|
| |
Push LR register before calling __gnu_mcount_nc as it expects the value of LR register to be the top value of
the stack on ARM32.
Differential Revision: https://reviews.llvm.org/D65019
llvm-svn: 369147
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
We tried to support EM_ASM with setjmp/longjmp in binaryen. But with dynamic
linking thrown into the mix, the code is no longer understandable and cannot
be maintained. We also discovered more bugs in the EM_ASM handling code.
To ensure maintainability and correctness of the binaryen code, EM_ASM will
no longer be supported with setjmp/longjmp. This is probably fine since the
support was added recently and haven't be published.
Reviewers: tlively, sbc100, jgravelle-google, kripken
Reviewed By: tlively, kripken
Subscribers: dschuff, hiraditya, aheejin, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66356
llvm-svn: 369137
|
| |
|
|
|
|
| |
Nothing calls this yet, everything still goes through the non (all) DemandedElts wrapper.
llvm-svn: 369136
|
| |
|
|
|
|
| |
Eventually we need to generalize combineExtractWithShuffle to handle all faux shuffles and handle truncate (and X86ISD::VTRUNC etc.) there, but we're not ready yet (still creates nodes on the fly, incomplete DemandedElts support, bad use of recursive Depth limit).
llvm-svn: 369134
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
instructions.
Recommit with fixes for mac builders.
Summary:
AArch64InstrInfo::getInstSizeInBytes is incorrectly treating meta
instructions (e.g. CFI_INSTRUCTION) as normal instructions and
giving them a size of 4.
This results in branch relaxation calculating block sizes wrong.
Branch relaxation also considers alignment and thus a single
mistake can result in later blocks being incorrectly sized even
when they themselves do not contain meta instructions.
The net result is we might not relax a branch whose destination is
not within range.
Reviewers: nickdesaulniers, peter.smith
Reviewed By: peter.smith
Subscribers: javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66337
> llvm-svn: 369111
llvm-svn: 369133
|
| |
|
|
|
|
|
|
| |
meta instructions.
This reverts r369111 (git commit 3ccee5f7c4087ed119dbeba537f3df1b048a4dff)
llvm-svn: 369132
|
| |
|
|
| |
llvm-svn: 369126
|
| |
|
|
| |
llvm-svn: 369124
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
callee-save area.
Changes:
There was a condition for `!NeedsFrameRecord` missing in the assert. The
assert in question has changed to:
+ assert((!RPI.isPaired() || !NeedsFrameRecord || RPI.Reg2 != AArch64::FP ||
+ RPI.Reg1 == AArch64::LR) &&
+ "FrameRecord must be allocated together with LR");
This addresses PR43016.
llvm-svn: 369122
|
| |
|
|
|
|
|
|
|
| |
MVE also has some sext of loads, which will be free just as scalar
instructions are.
Differential Revision: https://reviews.llvm.org/D66008
llvm-svn: 369118
|
| |
|
|
|
|
|
|
|
| |
Only in public interfaces that have not yet been converted should there remain
registers with unsigned type.
Differential Revision: https://reviews.llvm.org/D66252
llvm-svn: 369114
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
instructions.
Summary:
AArch64InstrInfo::getInstSizeInBytes is incorrectly treating meta
instructions (e.g. CFI_INSTRUCTION) as normal instructions and
giving them a size of 4.
This results in branch relaxation calculating block sizes wrong.
Branch relaxation also considers alignment and thus a single
mistake can result in later blocks being incorrectly sized even
when they themselves do not contain meta instructions.
The net result is we might not relax a branch whose destination is
not within range.
Reviewers: nickdesaulniers, peter.smith
Reviewed By: peter.smith
Subscribers: javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66337
llvm-svn: 369111
|
| |
|
|
|
|
| |
We don't use anything from TargetOptions.h directly and its included via TargetLowering.h anyhow.
llvm-svn: 369110
|