Because of different shell quoting rules, and the fact that LLDB
commands often contain spaces, -O is not portable for writing command
lines. Instead, we should use explicit lldbinit files.
Differential Revision: https://reviews.llvm.org/D54680
llvm-svn: 347213
This patch defines an interleaved-load-combine pass. The pass searches
for ShuffleVector instructions that represent interleaved loads. Matches are
converted such that they will be captured by the InterleavedAccessPass.
The pass extends LLVMs capabilities to use target specific instruction
selection of interleaved load patterns (e.g.: ld4 on Aarch64
architectures).
Differential Revision: https://reviews.llvm.org/D52653
llvm-svn: 347208
Summary:
Old behavior is to just return the cached entry regardless of opened-ness.
That feels buggy (though I guess nobody ever actually needed this).
This came up in the context of clangd+clang-tidy integration: we're
going to getFile(open=false) to replay preprocessor actions obscured by
the preamble, but the compilation may subsequently getFile(open=true)
for non-preamble includes.
Reviewers: ilya-biryukov
Subscribers: ioeric, kadircet, cfe-commits
Differential Revision: https://reviews.llvm.org/D54691
llvm-svn: 347205
Summary:
As it was pointed out in D54388+D54390, the maximal size of `Neighbors` is known,
it will contain at most Points_.size() minus one (the center of the cluster)
While that is the upper bound, meaning in the most cases, the actual count
will be much smaller, since D54390 made the allocation persistent,
we no longer have to worry about overly-optimistically `reserve()`ing.
Old: (D54393)
```
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html' (16 runs):
6553.167456 task-clock (msec) # 1.000 CPUs utilized ( +- 0.21% )
...
6.5547 +- 0.0134 seconds time elapsed ( +- 0.20% )
```
New:
```
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html' (16 runs):
6315.057872 task-clock (msec) # 0.999 CPUs utilized ( +- 0.24% )
...
6.3187 +- 0.0160 seconds time elapsed ( +- 0.25% )
```
And that is another -~4%.
Since this is the last (as of this moment) patch in this patch series,
it is a good time to summarize:
Old: (svn trunk, as stated in D54381)
```
$ time ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html &> /dev/null
real 0m24.884s
user 0m24.099s
sys 0m0.785s
```
So these patches, on a given benchmark,
has decreased llvm-exegesis analysis time by 74.62%.
There surely is more room for further improvements.
D54514 may improve thins by -11.5% more (relative to this patch).
Parallelization may improve things further significantly, too.
Reviewers: courbet, MaskRay, RKSimon, gchatelet, john.brawn
Reviewed By: courbet, MaskRay
Subscribers: tschuett, llvm-commits
Differential Revision: https://reviews.llvm.org/D54415
llvm-svn: 347204
Summary:
Test data: 500kLOC of benchmark.yaml, 23Mb. (that is a subset of the actual uops benchmark i was trying to analyze!)
Old time: (D54381)
```
$ time ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html &> /dev/null
real 0m10.487s
user 0m9.745s
sys 0m0.740s
```
New time:
```
$ time ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html &> /dev/null
real 0m9.599s
user 0m8.824s
sys 0m0.772s
```
Not that much, around -9%. But that is not the good part yet, again.
Old:
* calls to allocation functions: 3347676
* temporary allocations: 277818
* bytes allocated in total (ignoring deallocations): 10.52 GB
New:
* calls to allocation functions: 2109712 (-36%)
* temporary allocations: 33112 (-88%)
* bytes allocated in total (ignoring deallocations): 4.43 GB (-58% *sic*)
Reviewers: courbet, MaskRay, RKSimon, gchatelet, john.brawn
Reviewed By: courbet, MaskRay
Subscribers: tschuett, llvm-commits
Differential Revision: https://reviews.llvm.org/D54382
llvm-svn: 347198
Summary:
Test data: 500kLOC of benchmark.yaml, 23Mb. (that is a subset of the actual uops benchmark i was trying to analyze!)
Old time:
```
$ time ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html &> /dev/null
real 0m24.884s
user 0m24.099s
sys 0m0.785s
```
New time:
```
$ time ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html &> /dev/null
real 0m10.469s
user 0m9.797s
sys 0m0.672s
```
So -60%. And that isn't the good bit yet.
Old:
* calls to allocation functions: 106560180 (yes, 107 *million* allocations.)
* bytes allocated in total (ignoring deallocations): 12.17 GB
New:
* calls to allocation functions: 3347676 (-96.86%) (just 3 mil)
* bytes allocated in total (ignoring deallocations): 10.52 GB (~2GB less)
---
Two points i want to raise:
* `std::unordered_set<>` should not have been used there in the first place.
It is banned by the https://llvm.org/docs/ProgrammersManual.html#other-set-like-container-options
* There is no tests, so i'm not fully sure this is correct.
Since it was unordered set, i guess there are zero restrictions on the order, and anything will be ok?
* I tried other containers suggested in https://llvm.org/docs/ProgrammersManual.html#set-like-containers-std-set-smallset-setvector-etc,
this `llvm::SetVector<>` seems to be best here.
Reviewers: courbet, MaskRay, RKSimon, gchatelet, john.brawn
Reviewed By: courbet
Subscribers: kristina, bobsayshilol, tschuett, llvm-commits
Differential Revision: https://reviews.llvm.org/D54381
llvm-svn: 347197
Truncs are treated as sources if their produce a value of the same
type as the one we currently trying to promote. Truncs used to be
considered as a sink if their operand was the same value type.
We now allow smaller types in the search, so we should search through
truncs that produce a smaller value. These truncs can then be
converted to an AND mask.
This leaves sinks as being:
- points where the value in the register is being observed, such as
an icmp, switch or store.
- points where value types have to match, such as calls and returns.
- zext are included to ease the transformation and are generally
removed later on.
During this change, it also became apart from truncating sinks was
broken: if a sink used a source, its type information had already
been lost by the time the truncation happens. So I've changed the
method of caching the type information.
Differential Revision: https://reviews.llvm.org/D54515
llvm-svn: 347191
The general approach taken is to make note of loop invariant branches, then when
we see something conditional on that branch, such as a phi, we create a copy of
the branch and (empty versions of) its successors and hoist using that.
This has no impact by itself that I've been able to see, as LICM typically
doesn't see such phis as they will have been converted into selects by the time
LICM is run, but once we start doing phi-to-select conversion later it will be
important.
Differential Revision: https://reviews.llvm.org/D52827
llvm-svn: 347190
There is no variable-length shifts on MSP430. Therefore
"eat" 8 bits of shift via bswap & ext.
Path by Kristina Bessonova!
Differential Revision: https://reviews.llvm.org/D54623
llvm-svn: 347187
The shift requires a copy to avoid clobbering a register. Comparing with 0 uses an xor to produce 0 that will be overwritten with the compare results. So still requires 2 instructions, but should be one byte shorter since it doesn't need to encode an immediate.
llvm-svn: 347185
This patch introduces infrastructure and the simplest case for constant-folding
of branch and switch instructions within loop into unconditional branches.
It is useful as a cleanup for such passes as loop unswitching that sometimes
produce such branches.
Only the simplest case supported in this patch: after the folding, no block
should become dead or stop being part of the loop. Support for more
sophisticated cases will go separately in follow-up patches.
Differential Revision: https://reviews.llvm.org/D54021
Reviewed By: anna
llvm-svn: 347183
Every Analysis pass has a get method that returns a reference of the Result of
the Analysis, for example, BlockFrequencyInfo
&BlockFrequencyInfoWrapperPass::getBFI(). I believe that
ProfileSummaryInfo::getPSI() is the only exception to that, as it was returning
a pointer.
Another change is renaming isHotBB and isColdBB to isHotBlock and isColdBlock,
respectively. Most methods use BB as the argument of variable names while
methods usually refer to Basic Blocks as Blocks, instead of BB. For example,
Function::getEntryBlock, Loop:getExitBlock, etc.
I also fixed one of the comments.
Patch by Rodrigo Caetano Rocha!
Differential Revision: https://reviews.llvm.org/D54669
llvm-svn: 347182
Previously we used an arithmetic shift right by 31, but that requires a copy to preserve the input. So we might as well materialize a zero and compare to it since the comparison will overwrite the register that contains the zeros. This should be one byte shorter.
llvm-svn: 347181
Leave just the v4i8->v4i64 and v8i8->v8i64, but only enable them on pre-sse4.1 targets when 64-bit mode is enabled. In those cases we end up creating sext loads that get scalarized to code that looks better than what we get from loading into a vector register and doing a multiple step sign extend using unpacks and shifts.
llvm-svn: 347180
Pre-SSE4.1 sext_invec for v2i64 is complicated because we don't have a v2i64 sra instruction. So instead we sign extend to i32 using unpack and sra, then copy the elements and do a v4i32 sra to fill with sign bits, then interleave the i32 sign extend and the sign bits. So really we're doing to two sign extends but only using half of the v4i32 intermediate result.
When the result is more than 128 bits, default type legalization would prefer to split the destination type all the way down to v2i64 with shuffles followed by v16i8/v8i16->v2i64 sext_inreg operations. This results in more instructions than necessary because we are only utilizing the lower 2 elements of the v4i32 intermediate result. Instead we can custom split a v4i8/v4i16->v4i64 sign_extend. Then we can sign extend v4i8/v4i16->v4i32 invec producing a full v4i32 result. Create the sign bit vector as a v4i32 then split and interleave with the sign bits using an punpackldq and punpackhdq.
llvm-svn: 347176
Some of these sequeces look pretty bad since we have to copy the sign bit from a 32 bit register to a 64 bit register to finish a sign extend.
llvm-svn: 347175
If we widen illegal types instead of promoting, we should be able to rely on the type legalizer to create the vector_inreg operations for us with some caveats.
This patch disables combineToExtendVectorInReg when we are using widening.
I've enabled custom legalization for v8i8->v8i64 extends under avx512f since the type legalizer would want to create a vector_inreg with a v64i8 input type which isn't legal without avx512bw. So we go to v16i8 with custom code using the relaxation of rules we get from D54346.
I've also enable custom legalization of v8i64 and v16i32 operations with with AVX. When the input type is 128 bits, the default splitting legalization would extend first 128->256, then do the a split to two 128 pieces. Extend each half to 256 and then concat the result. The custom legalization I've added instead uses a 128->256 bit vector_inreg extend that only reads the lower 64-bits for the low half of the split. Then shuffles the high 64-bits to the low 64-bits and does another vector_inreg extend.
llvm-svn: 347172
Summary: This is an improvement over the two pshufbs and punpcklqdq we'd get otherwise.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D54671
llvm-svn: 347171
Sadly, this duplicates (twice) the logic from InstSimplify. There
might be some way to at least share the DAG versions of the code,
but copying the folds seems to be the standard method to ensure
that we don't miss these folds.
Unlike in IR, we don't run DAGCombiner to fixpoint, so there's no
way to ensure that we do these kinds of simplifications unless the
code is repeated at node creation time and during combines.
There were other tests that would become worthless with this
improvement that I changed as pre-commits:
rL347161
rL347164
rL347165
rL347166
rL347167
I'm not sure how to salvage the remaining tests (diffs in this patch).
So the x86 tests verify that the new code is working as intended.
The AMDGPU test is actually similar to my motivating case: we have
some undef value that has survived to machine IR in an x86 test, and
then it gets folded in some weird way, or we crash if we don't transfer
the undef flag. But we would have been better off never getting to that
point by doing these simplifications.
This will lead back to PR32023 someday...
https://bugs.llvm.org/show_bug.cgi?id=32023
llvm-svn: 347170
Refactor towards making this recursive (necessary for PR38243 rotation splat detection).
IsSplatVector returns the original vector source of the splat and the splat index.
GetSplatValue returns the scalar splatted value as an extraction from IsSplatVector.
llvm-svn: 347168
Zachary Turner