Support for the intrinsics that read from and write to global named registers
is added for r1, r2 and r13 (depending on the subtarget).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@208509 91177308-0d34-0410-b5e6-96231b3b80d8
If we have two unique values for a v2i64 build vector, this will always result
in two vector loads if we expand using shuffles. Only one is necessary.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205231 91177308-0d34-0410-b5e6-96231b3b80d8
sitofp from v2i32 to v2f64 ends up generating a SIGN_EXTEND_INREG v2i64 node
(and similarly for v2i16 and v2i8). Even though there are no sign-extension (or
algebraic shifts) for v2i64 types, we can handle v2i32 sign extensions by
converting two and from v2i64. The small trick necessary here is to shift the
i32 elements into the right lanes before the i32 -> f64 step. This is because
of the big Endian nature of the system, we need the i32 portion in the high
word of the i64 elements.
For v2i16 and v2i8 we can do the same, but we first use the default Altivec
shift-based expansion from v2i16 or v2i8 to v2i32 (by casting to v4i32) and
then apply the above procedure.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205146 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@202451 91177308-0d34-0410-b5e6-96231b3b80d8
subsequent changes are easier to review. About to fix some layering
issues, and wanted to separate out the necessary churn.
Also comment and sink the include of "Windows.h" in three .inc files to
match the usage in Memory.inc.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198685 91177308-0d34-0410-b5e6-96231b3b80d8
Encodings were checked against the Power ISA documents and double
checked against binutils.
This fixes PR17350.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191419 91177308-0d34-0410-b5e6-96231b3b80d8
This is the first of many upcoming patches for PowerPC fast
instruction selection support. This patch implements the minimum
necessary for a functional (but extremely limited) FastISel pass. It
allows the table-generated portions of the selector to be created and
used, but in most cases selection will fall back to the DAG selector.
None of the block terminator instructions are implemented yet, and
most interesting instructions require some special handling.
Therefore there aren't any new test cases with this patch. There will
be quite a few tests coming with future patches.
This patch adds the make/CMake support for the new code (including
tablegen -gen-fast-isel) and creates the FastISel object for PPC64 ELF
only. It instantiates the necessary virtual functions
(TargetSelectInstruction, TargetMaterializeConstant,
TargetMaterializeAlloca, tryToFoldLoadIntoMI, and FastLowerArguments),
but of these, only TargetMaterializeConstant contains any useful
implementation. This is present since the table-generated code
requires the ability to materialize integer constants for some
instructions.
This patch has been tested by building and running the
projects/test-suite code with -O0. All tests passed with the
exception of a couple of long-running tests that time out using -O0
code generation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187399 91177308-0d34-0410-b5e6-96231b3b80d8
structure not just a pointer. This implements that and thus fixes va_copy
on PPC32. Fixes#15286. Both bug and patch by Florian Zeitz!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187158 91177308-0d34-0410-b5e6-96231b3b80d8
in-tree implementations of TargetLoweringBase::isFMAFasterThanMulAndAdd in
order to resolve the following issues with fmuladd (i.e. optional FMA)
intrinsics:
1. On X86(-64) targets, ISD::FMA nodes are formed when lowering fmuladd
intrinsics even if the subtarget does not support FMA instructions, leading
to laughably bad code generation in some situations.
2. On AArch64 targets, ISD::FMA nodes are formed for operations on fp128,
resulting in a call to a software fp128 FMA implementation.
3. On PowerPC targets, FMAs are not generated from fmuladd intrinsics on types
like v2f32, v8f32, v4f64, etc., even though they promote, split, scalarize,
etc. to types that support hardware FMAs.
The function has also been slightly renamed for consistency and to force a
merge/build conflict for any out-of-tree target implementing it. To resolve,
see comments and fixed in-tree examples.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185956 91177308-0d34-0410-b5e6-96231b3b80d8
When accessing just a single CR register, it is always preferable to
use mfocrf instead of mfcr, if the former is available on the CPU.
Current code makes that distinction in many, but not all places
where a single CR register value is retrieved. One missing
location is PPCRegisterInfo::lowerCRSpilling.
To fix this and make this simpler in the future, this patch changes
the bulk of the back-end to always assume mfocrf is available and
simply generate it when needed.
On machines that actually do not support mfocrf, the instruction
is replaced by mfcr at the very end, in EmitInstruction.
This has the additional benefit that we no longer need the
MFCRpseud hack, since before EmitInstruction we always have
a MFOCRF instruction pattern, which already models data flow
as required.
The patch also adds the MFOCRF8 version of the instruction,
which was missing so far.
Except for the PPCRegisterInfo::lowerCRSpilling case, no change
in generated code intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185556 91177308-0d34-0410-b5e6-96231b3b80d8
This is a preparatory patch for fast-isel support. The instruction
selector will need to access some functions in PPCGenCallingConv.inc,
which in turn requires several helper functions to be defined. These
are currently defined near the only use of PCCGenCallingConv.inc,
inside PPCISelLowering.cpp. This patch moves the declaration of the
functions into the associated header file to provide the needed
visibility.
No functional change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183844 91177308-0d34-0410-b5e6-96231b3b80d8
Change SelectionDAG::getXXXNode() interfaces as well as call sites of
these functions to pass in SDLoc instead of DebugLoc.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182703 91177308-0d34-0410-b5e6-96231b3b80d8
This is the second part of the change to always return "true"
offset values from getPreIndexedAddressParts, tackling the
case of "memrix" type operands.
This is about instructions like LD/STD that only have a 14-bit
field to encode immediate offsets, which are implicitly extended
by two zero bits by the machine, so that in effect we can access
16-bit offsets as long as they are a multiple of 4.
The PowerPC back end currently handles such instructions by
carrying the 14-bit value (as it will get encoded into the
actual machine instructions) in the machine operand fields
for such instructions. This means that those values are
in fact not the true offset, but rather the offset divided
by 4 (and then truncated to an unsigned 14-bit value).
Like in the case fixed in r182012, this makes common code
operations on such offset values not work as expected.
Furthermore, there doesn't really appear to be any strong
reason why we should encode machine operands this way.
This patch therefore changes the encoding of "memrix" type
machine operands to simply contain the "true" offset value
as a signed immediate value, while enforcing the rules that
it must fit in a 16-bit signed value and must also be a
multiple of 4.
This change must be made simultaneously in all places that
access machine operands of this type. However, just about
all those changes make the code simpler; in many cases we
can now just share the same code for memri and memrix
operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182032 91177308-0d34-0410-b5e6-96231b3b80d8
The old PPCCTRLoops pass, like the Hexagon pass version from which it was
derived, could only handle some simple loops in canonical form. We cannot
directly adapt the new Hexagon hardware loops pass, however, because the
Hexagon pass contains a fundamental assumption that non-constant-trip-count
loops will contain a guard, and this is not always true (the result being that
incorrect negative counts can be generated). With this commit, we replace the
pass with a late IR-level pass which makes use of SE to calculate the
backedge-taken counts and safely generate the loop-count expressions (including
any necessary max() parts). This IR level pass inserts custom intrinsics that
are lowered into the desired decrement-and-branch instructions.
The most fragile part of this new implementation is that interfering uses of
the counter register must be detected on the IR level (and, on PPC, this also
includes any indirect branches in addition to function calls). Also, to make
all of this work, we need a variant of the mtctr instruction that is marked
as having side effects. Without this, machine-code level CSE, DCE, etc.
illegally transform the resulting code. Hopefully, this can be improved
in the future.
This new pass is smaller than the original (and much smaller than the new
Hexagon hardware loops pass), and can handle many additional cases correctly.
In addition, the preheader-creation code has been copied from LoopSimplify, and
after we decide on where it belongs, this code will be refactored so that it
can be explicitly shared (making this implementation even smaller).
The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for
the new Hexagon pass. There are a few classes of loops that this pass does not
transform (noted by FIXMEs in the files), but these deficiencies can be
addressed within the SE infrastructure (thus helping many other passes as well).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181927 91177308-0d34-0410-b5e6-96231b3b80d8
On cores for which we know the misprediction penalty, and we have
the isel instruction, we can profitably perform early if conversion.
This enables us to replace some small branch sequences with selects
and avoid the potential stalls from mispredicting the branches.
Enabling this feature required implementing canInsertSelect and
insertSelect in PPCInstrInfo; isel code in PPCISelLowering was
refactored to use these functions as well.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178926 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178617 91177308-0d34-0410-b5e6-96231b3b80d8
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).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178480 91177308-0d34-0410-b5e6-96231b3b80d8
PPCISD::STFIWX is really a memory opcode, and so it should come after
FIRST_TARGET_MEMORY_OPCODE, and we should use DAG.getMemIntrinsicNode to create
nodes using it.
No functionality change intended (although there could be optimization benefits
from preserving the MMO information).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178468 91177308-0d34-0410-b5e6-96231b3b80d8
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).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178446 91177308-0d34-0410-b5e6-96231b3b80d8
The existing SINT_TO_FP code for i32 -> float/double conversion was disabled
because it relied on broken EXTSW_32/STD_32 instruction definitions. The
original intent had been to enable these 64-bit instructions to be used on CPUs
that support them even in 32-bit mode. Unfortunately, this form of lying to
the infrastructure was buggy (as explained in the FIXME comment) and had
therefore been disabled.
This re-enables this functionality, using regular DAG nodes, but only when
compiling in 64-bit mode. The old STD_32/EXTSW_32 definitions (which were dead)
are removed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178438 91177308-0d34-0410-b5e6-96231b3b80d8
As part of the the sequence generated to implement long double -> int
conversions, we need to perform an FADD in round-to-zero mode. This is
problematical since the FPSCR is not at all modeled at the SelectionDAG
level, and thus there is a risk of getting floating point instructions
generated out of sequence with the instructions to modify FPSCR.
The current code handles this by somewhat "special" patterns that in part
have dummy operands, and/or duplicate existing instructions, making them
awkward to handle in the asm parser.
This commit changes this by leaving the "FADD in round-to-zero mode"
as an atomic operation on the SelectionDAG level, and only split it up into
real instructions at the MI level (via custom inserter). Since at *this*
level the FPSCR *is* modeled (via the "RM" hard register), much of the
"special" stuff can just go away, and the resulting patterns can be used by
the asm parser.
No significant change in generated code expected.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178006 91177308-0d34-0410-b5e6-96231b3b80d8
We currently have a duplicated set of call instruction patterns depending
on the ABI to be followed (Darwin vs. Linux). This is a bit odd; while the
different ABIs will result in different instruction sequences, the actual
instructions themselves ought to be independent of the ABI. And in fact it
turns out that the only nontrivial difference between the two sets of
patterns is that in the PPC64 Linux ABI, the instruction used for indirect
calls is marked to take X11 as extra input register (which is indeed used
only with that ABI to hold an incoming environment pointer for nested
functions). However, this does not need to be hard-coded at the .td
pattern level; instead, the C++ code expanding calls can simply add that
use, just like it adds uses for argument registers anyway.
No change in generated code expected.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177735 91177308-0d34-0410-b5e6-96231b3b80d8
This implements SJLJ lowering on PPC, making the Clang functions
__builtin_{setjmp/longjmp} functional on PPC platforms. The implementation
strategy is similar to that on X86, with the exception that a branch-and-link
variant is used to get the right jump address. Credit goes to Bill Schmidt for
suggesting the use of the unconditional bcl form (instead of the regular bl
instruction) to limit return-address-cache pollution.
Benchmarking the speed at -O3 of:
static jmp_buf env_sigill;
void foo() {
__builtin_longjmp(env_sigill,1);
}
main() {
...
for (int i = 0; i < c; ++i) {
if (__builtin_setjmp(env_sigill)) {
goto done;
} else {
foo();
}
done:;
}
...
}
vs. the same code using the libc setjmp/longjmp functions on a P7 shows that
this builtin implementation is ~4x faster with Altivec enabled and ~7.25x
faster with Altivec disabled. This comparison is somewhat unfair because the
libc version must also save/restore the VSX registers which we don't yet
support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177666 91177308-0d34-0410-b5e6-96231b3b80d8
Unaligned access is supported on PPC for non-vector types, and is generally
more efficient than manually expanding the loads and stores.
A few of the existing test cases were using expanded unaligned loads and stores
to test other features (like load/store with update), and for these test cases,
unaligned access remains disabled.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177160 91177308-0d34-0410-b5e6-96231b3b80d8
- ISD::SHL/SRL/SRA must have either both scalar or both vector operands
but TLI.getShiftAmountTy() so far only return scalar type. As a
result, backend logic assuming that breaks.
- Rename the original TLI.getShiftAmountTy() to
TLI.getScalarShiftAmountTy() and re-define TLI.getShiftAmountTy() to
return target-specificed scalar type or the same vector type as the
1st operand.
- Fix most TICG logic assuming TLI.getShiftAmountTy() a simple scalar
type.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176364 91177308-0d34-0410-b5e6-96231b3b80d8
Large code model is identical to medium code model except that the
addis/addi sequence for "local" accesses is never used. All accesses
use the addis/ld sequence.
The coding changes are straightforward; most of the patch is taken up
with creating variants of the medium model tests for large model.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175767 91177308-0d34-0410-b5e6-96231b3b80d8
This handles the cases where the 6-bit splat element is odd, converting
to a three-instruction sequence to add or subtract two splats. With this
fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175663 91177308-0d34-0410-b5e6-96231b3b80d8
During lowering of a BUILD_VECTOR, we look for opportunities to use a
vector splat. When the splatted value fits in 5 signed bits, a single
splat does the job. When it doesn't fit in 5 bits but does fit in 6,
and is an even value, we can splat on half the value and add the result
to itself.
This last optimization hasn't been working recently because of improved
constant folding. To circumvent this, create a pseudo VADD_SPLAT that
can be expanded during instruction selection.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175632 91177308-0d34-0410-b5e6-96231b3b80d8
for a wider range of GOT entries that can hold thread-relative offsets.
This matches the behavior of GCC, which was not documented in the PPC64 TLS
ABI. The ABI will be updated with the new code sequence.
Former sequence:
ld 9,x@got@tprel(2)
add 9,9,x@tls
New sequence:
addis 9,2,x@got@tprel@ha
ld 9,x@got@tprel@l(9)
add 9,9,x@tls
Note that a linker optimization exists to transform the new sequence into
the shorter sequence when appropriate, by replacing the addis with a nop
and modifying the base register and relocation type of the ld.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170209 91177308-0d34-0410-b5e6-96231b3b80d8
PowerPC target. This is the last of the four models, so we now have
full TLS support.
This is mostly a straightforward extension of the general dynamic model.
I had to use an additional Chain operand to tie ADDIS_DTPREL_HA to the
register copy following ADDI_TLSLD_L; otherwise everything above the
ADDIS_DTPREL_HA appeared dead and was removed.
As before, there are new test cases to test the assembly generation, and
the relocations output during integrated assembly. The expected code
gen sequence can be read in test/CodeGen/PowerPC/tls-ld.ll.
There are a couple of things I think can be done more efficiently in the
overall TLS code, so there will likely be a clean-up patch forthcoming;
but for now I want to be sure the functionality is in place.
Bill
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170003 91177308-0d34-0410-b5e6-96231b3b80d8
mention the inline memcpy / memset expansion code is a mess?
This patch split the ZeroOrLdSrc argument into two: IsMemset and ZeroMemset.
The first indicates whether it is expanding a memset or a memcpy / memmove.
The later is whether the memset is a memset of zero. It's totally possible
(likely even) that targets may want to do different things for memcpy and
memset of zero.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169959 91177308-0d34-0410-b5e6-96231b3b80d8
Also added more comments to explain why it is generally ok to return true.
- Rename getOptimalMemOpType argument IsZeroVal to ZeroOrLdSrc. It's meant to
be true for loaded source (memcpy) or zero constants (memset). The poor name
choice is probably some kind of legacy issue.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169954 91177308-0d34-0410-b5e6-96231b3b80d8
Given a thread-local symbol x with global-dynamic access, the generated
code to obtain x's address is:
Instruction Relocation Symbol
addis ra,r2,x@got@tlsgd@ha R_PPC64_GOT_TLSGD16_HA x
addi r3,ra,x@got@tlsgd@l R_PPC64_GOT_TLSGD16_L x
bl __tls_get_addr(x@tlsgd) R_PPC64_TLSGD x
R_PPC64_REL24 __tls_get_addr
nop
<use address in r3>
The implementation borrows from the medium code model work for introducing
special forms of ADDIS and ADDI into the DAG representation. This is made
slightly more complicated by having to introduce a call to the external
function __tls_get_addr. Using the full call machinery is overkill and,
more importantly, makes it difficult to add a special relocation. So I've
introduced another opcode GET_TLS_ADDR to represent the function call, and
surrounded it with register copies to set up the parameter and return value.
Most of the code is pretty straightforward. I ran into one peculiarity
when I introduced a new PPC opcode BL8_NOP_ELF_TLSGD, which is just like
BL8_NOP_ELF except that it takes another parameter to represent the symbol
("x" above) that requires a relocation on the call. Something in the
TblGen machinery causes BL8_NOP_ELF and BL8_NOP_ELF_TLSGD to be treated
identically during the emit phase, so this second operand was never
visited to generate relocations. This is the reason for the slightly
messy workaround in PPCMCCodeEmitter.cpp:getDirectBrEncoding().
Two new tests are included to demonstrate correct external assembly and
correct generation of relocations using the integrated assembler.
Comments welcome!
Thanks,
Bill
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169910 91177308-0d34-0410-b5e6-96231b3b80d8
