When targeting CPUs that don't have LDBRX, we end up producing code that is
very inefficient and large for this common idiom. This patch just
optimizes it two 32-bit LWBRX instructions along with a merge.
This fixes https://bugs.llvm.org/show_bug.cgi?id=49610
Differential revision: https://reviews.llvm.org/D104836
The is from discussion in https://reviews.llvm.org/D104247#inline-993387
The contract and reassoc flags shouldn't imply each other .
All the aggressive fsub fusion reassociate operations,
we should guard them with reassoc flag check.
Reviewed By: mcberg2017
Differential Revision: https://reviews.llvm.org/D104723
Summary:
generate eh_info when vector registers are saved according to the traceback table.
struct eh_info_t {
unsigned version; /* EH info version 0 */
#if defined(64BIT)
char _pad[4]; /* padding */
#endif
unsigned long lsda; /* Pointer to Language Specific Data Area */
unsigned long personality; /* Pointer to the personality routine */
};
the value of lsda and personality is zero when the number of vector registers saved is large zero and there is not personality of the function
Reviewers: Jason Liu
Differential Revision: https://reviews.llvm.org/D103651
According to IR LangRef, the FMF flag:
contract
Allow floating-point contraction (e.g. fusing a multiply followed by an
addition into a fused multiply-and-add).
reassoc
Allow reassociation transformations for floating-point instructions.
This may dramatically change results in floating-point.
My understanding is that these two flags shouldn't imply each other,
as we might have a SDNode that can be reassociated with others, but
not contractble.
eg: We may want following fmul/fad/fsub to freely reassoc, but don't
want fma being generated here.
%F = fmul reassoc double %A, %B ; <double> [#uses=1]
%G = fmul reassoc double %C, %D ; <double> [#uses=1]
%H = fadd reassoc double %F, %G ; <double> [#uses=1]
%I = fsub reassoc double %H, %E ; <double> [#uses=1]
Before https://reviews.llvm.org/D45710, `reassoc` flag actually
did not imply isContratable either.
The current implementation also only check the flag in fadd node,
ignoring fmul node, this patch update that as well.
Reviewed By: spatel, qiucf
Differential Revision: https://reviews.llvm.org/D104247
This can be seen as a follow up to commit 0ee439b705e82a4fe20e2,
that changed the second argument of __powidf2, __powisf2 and
__powitf2 in compiler-rt from si_int to int. That was to align with
how those runtimes are defined in libgcc.
One thing that seem to have been missing in that patch was to make
sure that the rest of LLVM also handle that the argument now depends
on the size of int (not using the si_int machine mode for 32-bit).
When using __builtin_powi for a target with 16-bit int clang crashed.
And when emitting libcalls to those rtlib functions, typically when
lowering @llvm.powi), the backend would always prepare the exponent
argument as an i32 which caused miscompiles when the rtlib was
compiled with 16-bit int.
The solution used here is to use an overloaded type for the second
argument in @llvm.powi. This way clang can use the "correct" type
when lowering __builtin_powi, and then later when emitting the libcall
it is assumed that the type used in @llvm.powi matches the rtlib
function.
One thing that needed some extra attention was that when vectorizing
calls several passes did not support that several arguments could
be overloaded in the intrinsics. This patch allows overload of a
scalar operand by adding hasVectorInstrinsicOverloadedScalarOpd, with
an entry for powi.
Differential Revision: https://reviews.llvm.org/D99439
We have added STXVP/LXVP for spilling and restoring the registers
but we neglected to add FI elimination code for these. The result
is that we end up producing impossible MachineInstr's that have
register operands in place of immediates.
Export `lq`, `stq`, `lqarx` and `stqcx.` in preparation for implementing 16-byte lock free atomic operations on AIX.
Add a new register class `g8prc` for these instructions, since these instructions require even-odd register pair.
Reviewed By: nemanjai, jsji, #powerpc
Differential Revision: https://reviews.llvm.org/D103010
GCC documentation for the `wa` constraint states that:
```
wa
A VSX register (VSR), vs0…vs63. This is either an FPR (vs0…vs31 are f0…f31)
or a VR (vs32…vs63 are v0…v31).
```
This technically means that we could accept floating point parameters. In fact,
gcc itself does. The following testcase compiles and runs on all PPC platforms with GCC,
whereas clang/llc will assert:
```
#include <stdio.h>
double foo ( vector double a ) {
double b, c;
asm("xvabsdp %x0, %x2 \n"
"xxsldwi %x1, %x0, %x0, 2 \n"
: "+wa" (b),
"=wa" (c)
: "wa" (a)
);
return b+c;
}
int main(void) {
vector double a = {-3., -4.};
double t = foo( a );
printf("%g\n", t);
}
```
This patch allows clang/llc to build and run this testcase.
Reviewed By: nemanjai, #powerpc
Differential Revision: https://reviews.llvm.org/D103409
Relaxing superclass constraint for VSX register classes helps reducing
32-byte spills and copies when register pressure is high.
In test case affected, some of them introduces more copies due to new
allocation order. However, this patch should not be the root cause, and
we may be able to fix it in other places of register allocation.
Reviewed By: nemanjai
Differential Revision: https://reviews.llvm.org/D104006
We will need to set the ssp canary bit in traceback table to communicate
with unwinder about the canary.
Reviewed By: #powerpc, shchenz
Differential Revision: https://reviews.llvm.org/D103202
When `-fstack-clash-protection` is enabled and stack has to be realigned, some parts of redzone is written prior the probe, so probe might overwrite content already written in redzone. To avoid it, we have to make sure the first probe is at full probe size or is the last probe so that we can skip redzone.
It also fixes violation of ABI under PPC where `r1` isn't updated atomically.
This fixes https://bugs.llvm.org/show_bug.cgi?id=49903.
Reviewed By: jsji
Differential Revision: https://reviews.llvm.org/D100290
PPC_FP128 determines isZero/isNan/isInf using high-order double value
only. Checking isZero/isNegative might return the isNullValue unexpectedly.
eg:
0xM0000000000000000FFFFFFFFFFFFFFFFF
isZero, but it is not NullValue.
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D103634
If we're not emitting separate fences for the success/failure cases, we
need to pass the merged ordering to the target so it can emit the
correct instructions.
For the PowerPC testcase, we end up with extra fences, but that seems
like an improvement over missing fences. If someone wants to improve
that, the PowerPC backed could be taught to emit the fences after isel,
instead of depending on fences emitted by AtomicExpand.
Fixes https://bugs.llvm.org/show_bug.cgi?id=33332 .
Differential Revision: https://reviews.llvm.org/D103342
The test CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll checks code
generation for constrained floating point intrinsics. Many test cases in
it were implemented using operations on constants. Constant folding of
constrained intrinsics would make these test cases almost useless,
because they would check only constant loading.
To keep the tests useful, operations on constants were replaced with
operations on function parameters.
Differential Revision: https://reviews.llvm.org/D103259
The code gen for f32 to i32 bitcast is not currently the most efficient;
this patch removes some unneccessary instructions gerneated.
Differential revision: https://reviews.llvm.org/D100782
The D35953, D62650 and D73691 introduced trimming of variables locations
in LiveDebugVariables pass, since there are some cases where after
the virtregrewrite we have exploded number of DBG_VALUEs created for some
inlined variables. As it looks, all problematic cases were regarding
inlined variables, so it seems reasonable to stop trimming the location
ranges for non-inlined variables.
It has very good impact on the llvm-locstats report.
Differential Revision: https://reviews.llvm.org/D102917
AIX use `__ssp_canary_word` instead of `__stack_chk_guard`.
This patch update the target hook to use correct symbol,
so that the basic stackprotect feature can work.
The traceback will be handled in follow up patch.
Reviewed By: #powerpc, shchenz
Differential Revision: https://reviews.llvm.org/D103100
This is the first in a series of patches to provide builtins for
compatibility with the XL compiler. Most of the builtins already had
intrinsics and only needed to be implemented in the front end.
Intrinsics were created for the three iospace builtins, eieio, and icbt.
Pseudo instructions were created for eieio and iospace_eieio to
ensure that nops were inserted before the eieio instruction.
Reviewed By: nemanjai, #powerpc
Differential Revision: https://reviews.llvm.org/D102443
We are using TOCEntry symbols like `LC..0` in TOC loads,
this is hard to read , at least requiring an additional step to figure
out the loaded symbols.
We should print out the name in comments.
Reviewed By: #powerpc, shchenz
Differential Revision: https://reviews.llvm.org/D102949
Since d6de1e1a71406c75a4ea4d5a2fe84289f07ea3a1, no attributes is quivalent to
setting attribute to false.
This is a preliminary commit for https://reviews.llvm.org/D99080
.byte supports string, so if the whole byte list are printable,
we can actually print the string for readability and LIT tests maintainence.
.byte 'H,'e,'l,'l,'o,',,' ,'w,'o,'r,'l,'d
->
.byte "Hello, world"
Reviewed By: hubert.reinterpretcast
Differential Revision: https://reviews.llvm.org/D102814
Unlike normal loads these don't have an extension field, but we know
from TargetLowering whether these are sign-extending or zero-extending,
and so can optimise away unnecessary extensions.
This was noticed on RISC-V, where sign extensions in the calling
convention would result in unnecessary explicit extension instructions,
but this also fixes some Mips inefficiencies. PowerPC sees churn in the
tests as all the zero extensions are only for promoting 32-bit to
64-bit, but these zero extensions are still not optimised away as they
should be, likely due to i32 being a legal type.
This also simplifies the WebAssembly code somewhat, which currently
works around the lack of target-independent combines with some ugly
patterns that break once they're optimised away.
Re-landed with correct handling in ComputeNumSignBits for Tmp == VTBits,
where zero-extending atomics were incorrectly returning 0 rather than
the (slightly confusing) required return value of 1.
Re-landed again after D102819 fixed PowerPC to correctly zero-extend all
of its atomics as it claimed to do, since the combination of that bug
and this optimisation caused buildbot regressions.
Reviewed By: RKSimon, atanasyan
Differential Revision: https://reviews.llvm.org/D101342
Partword atomic binaries are not zero extended as they should be.
This patch fixes them to ensure that they are zero extended.
Reviewed By: nemanjai, #powerpc
Differential Revision: https://reviews.llvm.org/D102819
These patterns are missing even though the underlying instruction
doesn't really care about the type. Added these patterns to resolve
https://bugs.llvm.org/show_bug.cgi?id=50084
This instruction is a nop on all server cores (certainly on all
cores that AIX supports) so it is fine to emit a nop instead of it.
In fact, that is exactly what XL emits. So we emit a nop on AIX
and we leave the codegen as is on other platforms since there may
indeed be cores out there for which this actually does some prefetching.
Added hashst to the prologue and hashchk to the epilogue.
The hash for the prologue and epilogue must always be stored as the first
element in the local variable space on the stack.
Reviewed By: nemanjai, #powerpc
Differential Revision: https://reviews.llvm.org/D99377
There are two reasons this shouldn't be restricted to Power8 and up:
1. For XL compatibility
2. Because clang will expand comparison operators to these intrinsics*
*Without this patch, the following causes a selection error:
int test(vector signed long a, vector signed long b) {
return a < b;
}
This patch provides the handling for the intrinsics in the back
end and removes the Power8 guards from the predicate functions
(vec_{all|any}_{eq|ne|gt|ge|lt|le}).
When an integer is converted into floating point in subword vector extract,
it can be done in 2 instructions instead of the 3+ instructions it generates
right now. This patch removes the uncessary generation.
Differential: https://reviews.llvm.org/D100604
The stack frame update code does not take into consideration spilling
to registers for callee saved registers. The option -ppc-enable-pe-vector-spills
turns on spilling to registers for callee saved registers and may expose a bug
in the code that moves a stack frame pointer update instruction.
Reviewed By: nemanjai, #powerpc
Differential Revision: https://reviews.llvm.org/D101366
It is an order of magnitude slower than the second slowest test
according to obj/llvm/test/.lit_test_times.txt.
The two slowest are:
2.870437e+02 CodeGen/PowerPC/aix-xcoff-huge-relocs.ll
2.850697e+01 tools/llvm-readobj/ELF/file-header-machine-types.test
Reviewed By: hubert.reinterpretcast
Differential Revision: https://reviews.llvm.org/D102190
If spills are to registers instead of to the stack then a copy will be used
and frame index scavenging is not required.
This patch adds debug info to frame index scavenging and makes sure that
spilling to registers does not cause frame index scavenging.
Reviewed By: nemanjai, #powerpc
Differential Revision: https://reviews.llvm.org/D101360
This is a simple fix on LE. On BE, vector shuffles are categorized into
different ops. We may need more work to eliminate these in
tablegen/pre-isel.
Reviewed By: nemanjai
Differential Revision: https://reviews.llvm.org/D101605
- Add branch absolute reloction R_RBA, R_TLS relocation for the variable offset
for the tlsgd model and R_TLSM for the region handle for the tlsgd model
- Properly set the relocation fixed values for R_TLS and R_TLSM
- Emit the TCEntry with the variant kind in the XCOFFStreamer
Reviewed by: sfertile, nemanjai, DiggerLin
Differential Revision: https://reviews.llvm.org/D100214
Unlike normal loads these don't have an extension field, but we know
from TargetLowering whether these are sign-extending or zero-extending,
and so can optimise away unnecessary extensions.
This was noticed on RISC-V, where sign extensions in the calling
convention would result in unnecessary explicit extension instructions,
but this also fixes some Mips inefficiencies. PowerPC sees churn in the
tests as all the zero extensions are only for promoting 32-bit to
64-bit, but these zero extensions are still not optimised away as they
should be, likely due to i32 being a legal type.
This also simplifies the WebAssembly code somewhat, which currently
works around the lack of target-independent combines with some ugly
patterns that break once they're optimised away.
Re-landed with correct handling in ComputeNumSignBits for Tmp == VTBits,
where zero-extending atomics were incorrectly returning 0 rather than
the (slightly confusing) required return value of 1.
Reviewed By: RKSimon, atanasyan
Differential Revision: https://reviews.llvm.org/D101342
This seems to have broken sanitizers, giving lots of
Assertion `NumBits <= MAX_INT_BITS && "bitwidth too large"' failed.
failures across multiple targets (currently X86 and PowerPC). Reverting
until I have a chance to reproduce and debug.
This reverts commit 6e876f9dedf00b24a96b8781e3b39d5282c43e91.
