Function pointers under PPC64 ELFv1 (which is used on PPC64/Linux on the
POWER7, A2 and earlier cores) are really pointers to a function descriptor, a
structure with three pointers: the actual pointer to the code to which to jump,
the pointer to the TOC needed by the callee, and an environment pointer. We
used to chain these loads, and make them opaque to the rest of the optimizer,
so that they'd always occur directly before the call. This is not necessary,
and in fact, highly suboptimal on embedded cores. Once the function pointer is
known, the loads can be performed ahead of time; in fact, they can be hoisted
out of loops.
Now these function descriptors are almost always generated by the linker, and
thus the contents of the descriptors are invariant. As a result, by default,
we'll mark the associated loads as invariant (allowing them to be hoisted out
of loops). I've added a target feature to turn this off, however, just in case
someone needs that option (constructing an on-stack descriptor, casting it to a
function pointer, and then calling it cannot be well-defined C/C++ code, but I
can imagine some JIT-compilation system doing so).
Consider this simple test:
$ cat call.c
typedef void (*fp)();
void bar(fp x) {
for (int i = 0; i < 1600000000; ++i)
x();
}
$ cat main.c
typedef void (*fp)();
void bar(fp x);
void foo() {}
int main() {
bar(foo);
}
On the PPC A2 (the BG/Q supercomputer), marking the function-descriptor loads
as invariant brings the execution time down to ~8 seconds from ~32 seconds with
the loads in the loop.
The difference on the POWER7 is smaller. Compiling with:
gcc -std=c99 -O3 -mcpu=native call.c main.c : ~6 seconds [this is 4.8.2]
clang -O3 -mcpu=native call.c main.c : ~5.3 seconds
clang -O3 -mcpu=native call.c main.c -mno-invariant-function-descriptors : ~4 seconds
(looks like we'd benefit from additional loop unrolling here, as a first
guess, because this is faster with the extra loads)
The -mno-invariant-function-descriptors will be added to Clang shortly.
llvm-svn: 226207
Patch by Kit Barton.
Support for the ICBT instruction is currently present, but limited to
embedded processors. This change adds a new FeatureICBT that can be used
to identify whether the ICBT instruction is available on a specific processor.
Two new tests are added:
* Positive test to ensure the icbt instruction is present when using
-mcpu=pwr8
* Negative test to ensure the icbt instruction is not generated when
using -mcpu=pwr7
Both test cases use the Prefetch opcode in LLVM. They are based on the
ppc64-prefetch.ll test case.
llvm-svn: 226033
Newer POWER cores, and the A2, support the cmpb instruction. This instruction
compares its operands, treating each of the 8 bytes in the GPRs separately,
returning a 'mask' result of 0 (for false) or -1 (for true) in each byte.
Code generation support is added, in the form of a PPCISelDAGToDAG
DAG-preprocessing routine, that recognizes patterns close to what the
instruction computes (either exactly, or related by a constant masking
operation), and generates the cmpb instruction (along with any necessary
constant masking operation). This can be expanded if use cases arise.
llvm-svn: 225106
This was missed last time around, for the P8 Instruction Scheduling
changes (223257). This will hook the P8Model entry in so those
changes will actually be used.
llvm-svn: 224452
CodeGen/PowerPC/vsx-p8.ll was failing.
'+power8-vector' is not a recognized feature for this target (ignoring feature)
llvm/test/CodeGen/PowerPC/vsx-p8.ll:33:14: error: expected string not found in input
; CHECK-REG: lxvw4x 34, 0, 3
^
<stdin>:50:2: note: scanning from here
.align 3
^
<stdin>:61:2: note: possible intended match here
lvx 3, 0, 3
^
llvm-svn: 223729
The current VSX feature for PowerPC specifies availability of the VSX
instructions added with the 2.06 architecture version. With 2.07, the
architecture adds new instructions to both the Category:Vector and
Category:VSX instruction sets. Additionally, unaligned vector storage
operations have improved performance.
This patch adds a feature to provide access to the new instructions
and performance capabilities of Power8. For compatibility with GCC,
the feature is controlled via a new -mpower8-vector switch, and the
feature causes the __POWER8_VECTOR__ builtin define to be generated by
the preprocessor.
There is a companion patch for cfe being committed at the same time.
llvm-svn: 219501
Older Book-E cores, such as the PPC 440, support only msync (which has the same
encoding as sync 0), but not any of the other sync forms. Newer Book-E cores,
however, do support sync, and for performance reasons we should allow the use
of the more-general form.
This refactors msync use into its own feature group so that it applies by
default only to older Book-E cores (of the relevant cores, we only have
definitions for the PPC440/450 currently).
llvm-svn: 218923
While LLVM now supports both ELFv1 and ELFv2 ABIs, their use is currently
hard-coded via the target triple: powerpc64-linux is always ELFv1, while
powerpc64le-linux is always ELFv2.
These are of course the most common scenarios, but in principle it is
possible to support the ELFv2 ABI on big-endian or the ELFv1 ABI on
little-endian systems (and GCC does support that), and there are some
special use cases for that (e.g. certain Linux kernel versions could
only be built using ELFv1 on LE).
This patch implements the LLVM side of supporting this. As precedent
on other platforms suggests, ABI options are passed to the back-end as
features. Thus, this patch implements two features "elfv1" and "elfv2"
that select the desired ABI if present. (If not, the LLVM uses the
same default rules as now.)
llvm-svn: 214072
includes handling DIR_PWR8 where appropriate
The P7Model Itinerary is currently tied in for use under the P8Model, and will be updated later.
llvm-svn: 211779
TableGen will create a lookup table for the A-type FMA instructions providing
their corresponding M-form opcodes. This will be used by upcoming commits.
llvm-svn: 204746
VSX is an ISA extension supported on the POWER7 and later cores that enhances
floating-point vector and scalar capabilities. Among other things, this adds
<2 x double> support and generally helps to reduce register pressure.
The interesting part of this ISA feature is the register configuration: there
are 64 new 128-bit vector registers, the 32 of which are super-registers of the
existing 32 scalar floating-point registers, and the second 32 of which overlap
with the 32 Altivec vector registers. This makes things like vector insertion
and extraction tricky: this can be free but only if we force a restriction to
the right register subclass when needed. A new "minipass" PPCVSXCopy takes care
of this (although it could do a more-optimal job of it; see the comment about
unnecessary copies below).
Please note that, currently, VSX is not enabled by default when targeting
anything because it is not yet ready for that. The assembler and disassembler
are fully implemented and tested. However:
- CodeGen support causes miscompiles; test-suite runtime failures:
MultiSource/Benchmarks/FreeBench/distray/distray
MultiSource/Benchmarks/McCat/08-main/main
MultiSource/Benchmarks/Olden/voronoi/voronoi
MultiSource/Benchmarks/mafft/pairlocalalign
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
SingleSource/Benchmarks/CoyoteBench/almabench
SingleSource/Benchmarks/Misc/matmul_f64_4x4
- The lowering currently falls back to using Altivec instructions far more
than it should. Worse, there are some things that are scalarized through the
stack that shouldn't be.
- A lot of unnecessary copies make it past the optimizers, and this needs to
be fixed.
- Many more regression tests are needed.
Normally, I'd fix these things prior to committing, but there are some
students and other contributors who would like to work this, and so it makes
sense to move this development process upstream where it can be subject to the
regular code-review procedures.
llvm-svn: 203768
There are currently two schemes for mapping instruction operands to
instruction-format variables for generating the instruction encoders and
decoders for the assembler and disassembler respectively: a) to map by name and
b) to map by position.
In the long run, we'd like to remove the position-based scheme and use only
name-based mapping. Unfortunately, the name-based scheme currently cannot deal
with complex operands (those with suboperands), and so we currently must use
the position-based scheme for those. On the other hand, the position-based
scheme cannot deal with (register) variables that are split into multiple
ranges. An upcoming commit to the PowerPC backend (adding VSX support) will
require this capability. While we could teach the position-based scheme to
handle that, since we'd like to move away from the position-based mapping
generally, it seems silly to teach it new tricks now. What makes more sense is
to allow for partial transitioning: use the name-based mapping when possible,
and only use the position-based scheme when necessary.
Now the problem is that mixing the two sensibly was not possible: the
position-based mapping would map based on position, but would not skip those
variables that were mapped by name. Instead, the two sets of assignments would
overlap. However, I cannot currently change the current behavior, because there
are some backends that rely on it [I think mistakenly, but I'll send a message
to llvmdev about that]. So I've added a new TableGen bit variable:
noNamedPositionallyEncodedOperands, that can be used to cause the
position-based mapping to skip variables mapped by name.
llvm-svn: 203767
This change enables tracking i1 values in the PowerPC backend using the
condition register bits. These bits can be treated on PowerPC as separate
registers; individual bit operations (and, or, xor, etc.) are supported.
Tracking booleans in CR bits has several advantages:
- Reduction in register pressure (because we no longer need GPRs to store
boolean values).
- Logical operations on booleans can be handled more efficiently; we used to
have to move all results from comparisons into GPRs, perform promoted
logical operations in GPRs, and then move the result back into condition
register bits to be used by conditional branches. This can be very
inefficient, because the throughput of these CR <-> GPR moves have high
latency and low throughput (especially when other associated instructions
are accounted for).
- On the POWER7 and similar cores, we can increase total throughput by using
the CR bits. CR bit operations have a dedicated functional unit.
Most of this is more-or-less mechanical: Adjustments were needed in the
calling-convention code, support was added for spilling/restoring individual
condition-register bits, and conditional branch instruction definitions taking
specific CR bits were added (plus patterns and code for generating bit-level
operations).
This is enabled by default when running at -O2 and higher. For -O0 and -O1,
where the ability to debug is more important, this feature is disabled by
default. Individual CR bits do not have assigned DWARF register numbers,
and storing values in CR bits makes them invisible to the debugger.
It is critical, however, that we don't move i1 values that have been promoted
to larger values (such as those passed as function arguments) into bit
registers only to quickly turn around and move the values back into GPRs (such
as happens when values are returned by functions). A pair of target-specific
DAG combines are added to remove the trunc/extends in:
trunc(binary-ops(binary-ops(zext(x), zext(y)), ...)
and:
zext(binary-ops(binary-ops(trunc(x), trunc(y)), ...)
In short, we only want to use CR bits where some of the i1 values come from
comparisons or are used by conditional branches or selects. To put it another
way, if we can do the entire i1 computation in GPRs, then we probably should
(on the POWER7, the GPR-operation throughput is higher, and for all cores, the
CR <-> GPR moves are expensive).
POWER7 test-suite performance results (from 10 runs in each configuration):
SingleSource/Benchmarks/Misc/mandel-2: 35% speedup
MultiSource/Benchmarks/Prolangs-C++/city/city: 21% speedup
MultiSource/Benchmarks/MiBench/automotive-susan: 23% speedup
SingleSource/Benchmarks/CoyoteBench/huffbench: 13% speedup
SingleSource/Benchmarks/Misc-C++/Large/sphereflake: 13% speedup
SingleSource/Benchmarks/Misc-C++/mandel-text: 10% speedup
SingleSource/Benchmarks/Misc-C++-EH/spirit: 10% slowdown
MultiSource/Applications/lemon/lemon: 8% slowdown
llvm-svn: 202451
The tests for the disassembler were adapted from the encoder tests, and for the
most part, the output from the disassembler matches that encoder-test inputs.
There are some places where more-informative mnemonics could be produced
(notably for the branch instructions), and those cases are noted in the tests
with FIXMEs.
Future work includes:
- Generating more-informative mnemonics when possible (this may also be done
in the printer).
- Remove the dependence on positional "numbered" operand-to-variable mapping
(for both encoding and decoding).
- Internally using 64-bit instruction variants in 64-bit mode (if this turns
out to matter).
llvm-svn: 197693
This adds a scheduling model for the POWER7 (P7) core, and enables the
machine-instruction scheduler when targeting the P7. Scheduling for the P7,
like earlier ooo PPC cores, requires considering both dispatch group hazards,
and functional unit resources and latencies. These are both modeled in a
combined itinerary. Dispatch group formation is still handled by the post-RA
scheduler (which still needs to be updated for the P7, but nevertheless does a
pretty good job).
One interesting aspect of this change is that I've also enabled to use of AA
duing CodeGen for the P7 (just as it is for the embedded cores). The benchmark
results seem to support this decision (see below), and while this is normally
useful for in-order cores, and not for ooo cores like the P7, I think that the
dispatch slot hazards are enough like in-order resources to make the AA useful.
Test suite significant performance differences (where negative is a speedup,
and positive is a regression) vs. the current situation:
MultiSource/Benchmarks/BitBench/drop3/drop3
with AA: N/A
without AA: -28.7614% +/- 19.8356%
(significantly against AA)
MultiSource/Benchmarks/FreeBench/neural/neural
with AA: -17.7406% +/- 11.2712%
without AA: N/A
(significantly in favor of AA)
MultiSource/Benchmarks/SciMark2-C/scimark2
with AA: -11.2079% +/- 1.80543%
without AA: -11.3263% +/- 2.79651%
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt
with AA: -41.8649% +/- 17.0053%
without AA: -34.5256% +/- 23.7072%
MultiSource/Benchmarks/mafft/pairlocalalign
with AA: 25.3016% +/- 17.8614%
without AA: 38.6629% +/- 14.9391%
(significantly in favor of AA)
MultiSource/Benchmarks/sim/sim
with AA: N/A
without AA: 13.4844% +/- 7.18195%
(significantly in favor of AA)
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
with AA: 15.0664% +/- 6.70216%
without AA: 12.7747% +/- 8.43043%
SingleSource/Benchmarks/BenchmarkGame/puzzle
with AA: 82.2713% +/- 26.3567%
without AA: 75.7525% +/- 41.1842%
SingleSource/Benchmarks/Misc/flops-2
with AA: -37.1621% +/- 20.7964%
without AA: -35.2342% +/- 20.2999%
(significantly in favor of AA)
These are 99.5% confidence intervals from 5 runs per configuration. Regarding
the choice to turn on AA during CodeGen, of these results, four seem
significantly in favor of using AA, and one seems significantly against. I'm
not making this decision based on these numbers alone, but these results
seem consistent with results I have from other tests, and so I think that, on
balance, using AA is a win.
llvm-svn: 195981
Use the new instruction deprecation feature to mark mftb (now replaced with
mfspr) and dst (along with the other Altivec cache control instructions) as
deprecated when targeting cores supporting at least ISA v2.03.
llvm-svn: 190605
Modern PPC cores support a floating-point copysign instruction, and we can use
this to lower the FCOPYSIGN node (which is created from calls to the libm
copysign function). A couple of extra patterns are necessary because the
operand types of FCOPYSIGN need not agree.
llvm-svn: 188653
This patch provides basic support for powerpc64le as an LLVM target.
However, use of this target will not actually generate little-endian
code. Instead, use of the target will cause the correct little-endian
built-in defines to be generated, so that code that tests for
__LITTLE_ENDIAN__, for example, will be correctly parsed for
syntax-only testing. Code generation will otherwise be the same as
powerpc64 (big-endian), for now.
The patch leaves open the possibility of creating a little-endian
PowerPC64 back end, but there is no immediate intent to create such a
thing.
The LLVM portions of this patch simply add ppc64le coverage everywhere
that ppc64 coverage currently exists. There is nothing of any import
worth testing until such time as little-endian code generation is
implemented. In the corresponding Clang patch, there is a new test
case variant to ensure that correct built-in defines for little-endian
code are generated.
llvm-svn: 187179
This adds support for the basic mnemoics (with the L operand) for the
fixed-point compare instructions. These are defined as aliases for the
already existing CMPW/CMPD patterns, depending on the value of L.
This requires use of InstAlias patterns with immediate literal operands.
To make this work, we need two further changes:
- define a RegisterPrefix, because otherwise literals 0 and 1 would
be parsed as literal register names
- provide a PPCAsmParser::validateTargetOperandClass routine to
recognize immediate literals (like ARM does)
llvm-svn: 185826
This adds assembler parser support to the PowerPC back end.
The parser will run for any powerpc-*-* and powerpc64-*-* triples,
but was tested only on 64-bit Linux. The supported syntax is
intended to be compatible with the GNU assembler.
The parser does not yet support all PowerPC instructions, but
it does support anything that is generated by LLVM itself.
There is no support for testing restricted instruction sets yet,
i.e. the parser will always accept any instructions it knows,
no matter what feature flags are given.
Instruction operands will be checked for validity and errors
generated. (Error handling in general could still be improved.)
The patch adds a number of test cases to verify instruction
and operand encodings. The tests currently cover all instructions
from the following PowerPC ISA v2.06 Book I facilities:
Branch, Fixed-point, Floating-Point, and Vector.
Note that a number of these instructions are not yet supported
by the back end; they are marked with FIXME.
A number of follow-on check-ins will add extra features. When
they are all included, LLVM passes all tests (including bootstrap)
when using clang -cc1as as the system assembler.
llvm-svn: 181050
This is prep. work for the implementation of optimizeCompare. Many PPC
instructions have 'record' forms (in almost all cases, this means that the RC
bit is set) that cause the result of the instruction to be compared with zero,
and the result of that comparison saved in a predefined condition register. In
order to add the record forms of the instructions without too much
copy-and-paste, the relevant functions have been refactored into multiclasses
which define both the record and normal forms.
Also, two TableGen-generated mapping functions have been added which allow
querying the instruction code for the record form given the normal form (and
vice versa).
No functionality change intended.
llvm-svn: 179356
When unsafe FP math operations are enabled, we can use the fre[s] and
frsqrte[s] instructions, which generate reciprocal (sqrt) estimates, together
with some Newton iteration, in order to quickly generate floating-point
division and sqrt results. All of these instructions are separately optional,
and so each has its own feature flag (except for the Altivec instructions,
which are covered under the existing Altivec flag). Doing this is not only
faster than using the IEEE-compliant fdiv/fsqrt instructions, but allows these
computations to be pipelined with other computations in order to hide their
overall latency.
I've also added a couple of missing fnmsub patterns which turned out to be
missing (but are necessary for good code generation of the Newton iterations).
Altivec needs a similar fix, but that will probably be more complicated because
fneg is expanded for Altivec's v4f32.
llvm-svn: 178617
The P7 and A2 have additional floating-point conversion instructions which
allow a direct two-instruction sequence (plus load/store) to convert from all
combinations (signed/unsigned i32/i64) <--> (float/double) (on previous cores,
only some combinations were directly available).
llvm-svn: 178480
This instruction is available on modern PPC64 CPUs, and is now used
to improve the SINT_TO_FP lowering (by eliminating the need for the
separate sign extension instruction and decreasing the amount of
needed stack space).
llvm-svn: 178446
These instructions are available on the P5x (and later) and on the A2. They
implement the standard floating-point rounding operations (floor, trunc, etc.).
One caveat: frin (round to nearest) does not implement "ties to even", and so
is only enabled in fast-math mode.
llvm-svn: 178337
These are 64-bit load/store with byte-swap, and available on the P7 and the A2.
Like the similar instructions for 16- and 32-bit words, these are matched in the
target DAG-combine phase against load/store-bswap pairs.
llvm-svn: 178276
PPC ISA 2.06 (P7, A2, etc.) has a popcntd instruction. Add this instruction and
tell TTI about it so that popcount-loop recognition will know about it.
llvm-svn: 178233
This is the first commit of a large series which will add support for the
QPX vector instruction set to the PowerPC backend. This instruction set is
used on the IBM Blue Gene/Q supercomputers.
llvm-svn: 173973
POWER4 is a 64-bit CPU (better matched to the 970).
The g3 is really the 750 (no altivec), the g4+ is the 74xx (not the 750).
Patch by Andreas Tobler.
llvm-svn: 158363
The PPC target feature gpul (IsGigaProcessor) was only used for one thing:
To enable the generation of the MFOCRF instruction. Furthermore, this
instruction is available on other PPC cores outside of the G5 line. This
feature now corresponds to the HasMFOCRF flag.
No functionality change.
llvm-svn: 158323
Hal Finkel