With the testcase for pr3120, the "threaded interpreter" runtime decreases
from 1788 to 1413 with this change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89877 91177308-0d34-0410-b5e6-96231b3b80d8
it is definitely profitable to tail duplicate indirect branches for x86.
This is likely to be true to various degrees for all modern x86 processors.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89865 91177308-0d34-0410-b5e6-96231b3b80d8
Make tail duplication of indirect branches much more aggressive (for targets
that indicate that it is profitable), based on further experience with
this transformation. I compiled 3 large applications with and without
this more aggressive tail duplication and measured minimal changes in code
size. ("size" on Darwin seems to round the text size up to the nearest
page boundary, so I can only say that any code size increase was less than
one 4k page.) Radar 7421267.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89814 91177308-0d34-0410-b5e6-96231b3b80d8
This violates the ABI (that area is "reserved"), and
while it is safe if all code is generated with current
compilers, there is some very old code around that uses
that slot for something else, and breaks if it is stored
into. Adjust testcases looking for current behavior.
I've verified that the stack frame size is right in all
testcases, whether it changed or not. 7311323.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89811 91177308-0d34-0410-b5e6-96231b3b80d8
than doing the same via constpool:
1. Load from constpool costs 3 cycles on A9, movt/movw pair - just 2.
2. Load from constpool might stall up to 300 cycles due to cache miss.
3. Movt/movw does not use load/store unit.
4. Less constpool entries => better compiler performance.
This is only enabled on ELF systems, since darwin does not have needed
relocations (yet).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89720 91177308-0d34-0410-b5e6-96231b3b80d8
way for each TargetJITInfo subclass to allocate its own stubs. This
means stubs aren't as exactly-sized anymore, but it lets us get rid of
TargetJITInfo::emitFunctionStubAtAddr(), which lets ARM and PPC
support the eager JIT, fixing http://llvm.org/PR4816.
* Rename the JITEmitter's stub creation functions to describe the kind
of stub they create. So far, all of them create lazy-compilation
stubs, but they sometimes get used when far-call stubs are needed.
Fixing http://llvm.org/PR5201 will involve fixing this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89715 91177308-0d34-0410-b5e6-96231b3b80d8
Note that "hasDotLocAndDotFile"-style debug info was already broken;
people wanting this functionality should implement it in the
AsmPrinter/DwarfWriter code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89711 91177308-0d34-0410-b5e6-96231b3b80d8
It's probably better in the long run to replace the
indirect-GlobalVariable system. That'll be done after a subsequent
patch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89708 91177308-0d34-0410-b5e6-96231b3b80d8
This fixes the NEON asm printing so the "predicate" field is printed between the opcode and the data type suffix.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89706 91177308-0d34-0410-b5e6-96231b3b80d8
VDUPLND and VDUPLNQ to derive from N2V instead of N2VDup. VDUPLND and VDUPLNQ
now expect op19_18 and op17_16 as the first two args.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89699 91177308-0d34-0410-b5e6-96231b3b80d8
Also fixed the corresponding testcase, and the PALIGNR
intrinsic (tested for correctness with llvm-gcc).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89491 91177308-0d34-0410-b5e6-96231b3b80d8
constant pool ranges, as CPEIsInRange() makes conservative assumptions about
the potential alignment changes from branch adjustments. The verification,
on the other hand, runs after those branch adjustments are made, so the
effects on alignment are known and already taken into account. The sanity
check in verify should check the range directly instead.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89473 91177308-0d34-0410-b5e6-96231b3b80d8
assembly can confuse things utterly, as it's assumed that instructions in
inline assembly are 4 bytes wide. For Thumb mode, that's often not true,
so the calculations for when alignment padding will be present get thrown off,
ultimately leading to out of range constant pool entry references. Making
more conservative assumptions that padding may be necessary when inline asm
is present avoids this situation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89403 91177308-0d34-0410-b5e6-96231b3b80d8
fully specified at this level. Subclasses of NLdStLN can specify selective
bit(s) for Inst{7-4}, as is done for VLD[234]LN* and VST[234]LN* inside
ARMInstrNEON.td.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89377 91177308-0d34-0410-b5e6-96231b3b80d8
contents of the block to be duplicated. Use this for ARM Cortex A8/9 to
be more aggressive tail duplicating indirect branches, since it makes it
much more likely that they will be predicted in the branch target buffer.
Testcase coming soon.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89187 91177308-0d34-0410-b5e6-96231b3b80d8
This is probably not confined to *just* these two things.
Anyway, the llvm-gcc front-end may look up the structure layout information for
an abstract type. That information will be stored into a table with the FE's
TD. Instruction combine can come along and also ask for information on that
abstract type, but for a separate TD (the one associated with the pass manager).
After the type is refined, the old structure layout information in the pass
manager's TD file is out of date. If a new type is allocated in the same space
as the old-unrefined type, then the structure type information in the pass
manager's TD file will be wrong, but won't know it.
Fix this by making the TD's structure type information an abstract type user.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89176 91177308-0d34-0410-b5e6-96231b3b80d8
0b1110 (ALways). This is so that the disassembler decoder can distinguish among
BX_RET, BRIND, and BXr9.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89000 91177308-0d34-0410-b5e6-96231b3b80d8
The large code model is documented at
http://www.x86-64.org/documentation/abi.pdf and says that calls should
assume their target doesn't live within the 32-bit pc-relative offset
that fits in the call instruction.
To do this, we turn off the global-address->target-global-address
conversion in X86TargetLowering::LowerCall(). The first attempt at
this broke the lazy JIT because it can separate the movabs(imm->reg)
from the actual call instruction. The lazy JIT receives the address of
the movabs as a relocation and needs to record the return address from
the call; and then when that call happens, it needs to patch the
movabs with the newly-compiled target. We could thread the call
instruction into the relocation and record the movabs<->call mapping
explicitly, but that seems to require at least as much new
complication in the code generator as this change.
To fix this, we make lazy functions _always_ go through a call
stub. You'd think we'd only have to force lazy calls through a stub on
difficult platforms, but that turns out to break indirect calls
through a function pointer. The right fix for that is to distinguish
between calls and address-of operations on uncompiled functions, but
that's complex enough to leave for someone else to do.
Another attempt at this defined a new CALL64i pseudo-instruction,
which expanded to a 2-instruction sequence in the assembly output and
was special-cased in the X86CodeEmitter's emitInstruction()
function. That broke indirect calls in the same way as above.
This patch also removes a hack forcing Darwin to the small code model.
Without far-call-stubs, the small code model requires things of the
JITMemoryManager that the DefaultJITMemoryManager can't provide.
Thanks to echristo for lots of testing!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@88984 91177308-0d34-0410-b5e6-96231b3b80d8