The VSX instruction set has two types of FMA instructions: A-type (where the
addend is taken from the output register) and M-type (where one of the product
operands is taken from the output register). This adds a small pass that runs
just after MI scheduling (and, thus, just before register allocation) that
mutates A-type instructions (that are created during isel) into M-type
instructions when:
1. This will eliminate an otherwise-necessary copy of the addend
2. One of the product operands is killed by the instruction
The "right" moment to make this decision is in between scheduling and register
allocation, because only there do we know whether or not one of the product
operands is killed by any particular instruction. Unfortunately, this also
makes the implementation somewhat complicated, because the MIs are not in SSA
form and we need to preserve the LiveIntervals analysis.
As a simple example, if we have:
%vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
...
%vreg9<def,tied1> = XSMADDADP %vreg9<tied0>, %vreg17, %vreg19,
%RM<imp-use>; VSLRC:%vreg9,%vreg17,%vreg19
...
We can eliminate the copy by changing from the A-type to the
M-type instruction. This means:
%vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16,
%RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16
is replaced by:
%vreg16<def,tied1> = XSMADDMDP %vreg16<tied0>, %vreg18, %vreg9,
%RM<imp-use>; VSLRC:%vreg16,%vreg18,%vreg9
and we remove: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204768 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@203768 91177308-0d34-0410-b5e6-96231b3b80d8
A setting in MCAsmInfo defines the "assembler dialect" to use. This is used
by common code to choose between alternatives in a multi-alternative GNU
inline asm statement like the following:
__asm__ ("{sfe|subfe} %0,%1,%2" : "=r" (out) : "r" (in1), "r" (in2));
The meaning of these dialects is platform specific, and GCC defines those
for PowerPC to use dialect 0 for old-style (POWER) mnemonics and 1 for
new-style (PowerPC) mnemonics, like in the example above.
To be compatible with inline asm used with GCC, LLVM ought to do the same.
Specifically, this means we should always use assembler dialect 1 since
old-style mnemonics really aren't supported on any current platform.
However, the current LLVM back-end uses:
AssemblerDialect = 1; // New-Style mnemonics.
in PPCMCAsmInfoDarwin, and
AssemblerDialect = 0; // Old-Style mnemonics.
in PPCLinuxMCAsmInfo.
The Linux setting really isn't correct, we should be using new-style
mnemonics everywhere. This is changed by this commit.
Unfortunately, the setting of this variable is overloaded in the back-end
to decide whether or not we are on a Darwin target. This is done in
PPCInstPrinter (the "SyntaxVariant" is initialized from the MCAsmInfo
AssemblerDialect setting), and also in PPCMCExpr. Setting AssemblerDialect
to 1 for both Darwin and Linux no longer allows us to make this distinction.
Instead, this patch uses the MCSubtargetInfo passed to createPPCMCInstPrinter
to distinguish Darwin targets, and ignores the SyntaxVariant parameter.
As to PPCMCExpr, this patch adds an explicit isDarwin argument that needs
to be passed in by the caller when creating a target MCExpr. (To do so
this patch implicitly also reverts commit 184441.)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185858 91177308-0d34-0410-b5e6-96231b3b80d8
This adds support for the last missing construct to parse TLS-related
assembler code:
add 3, 4, symbol@tls
The ADD8TLS currently hard-codes the @tls into the assembler string.
This cannot be handled by the asm parser, since @tls is parsed as
a symbol variant. This patch changes ADD8TLS to have the @tls suffix
printed as symbol variant on output too, which allows us to remove
the isCodeGenOnly marker from ADD8TLS. This in turn means that we
can add a AsmOperand to accept @tls marked symbols on input.
As a side effect, this means that the fixup_ppc_tlsreg fixup type
is no longer necessary and can be merged into fixup_ppc_nofixup.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185692 91177308-0d34-0410-b5e6-96231b3b80d8
This renames more VK_PPC_ enums, to make them more closely reflect
the @modifier string they represent. This also prepares for adding
a bunch of new VK_PPC_ enums in upcoming patches.
For consistency, some MO_ flags related to VK_PPC_ enums are
likewise renamed.
No change in behaviour.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184547 91177308-0d34-0410-b5e6-96231b3b80d8
The isDarwin parameter to the llvm::LowerPPCMachineInstrToMCInst
routine is now no longer needed; remove it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184441 91177308-0d34-0410-b5e6-96231b3b80d8
When asserts are enabled, this adds a verification pass for PPC counter-loop
formation. Unfortunately, without sacrificing code quality, there is no better
way of forming counter-based loops except at the (late) IR level. This means
that we need to recognize, at the IR level, anything which might turn into a
function call (or indirect branch). Because this is currently a finite set of
things, and because SelectionDAG lowering is basic-block local, this can be
done. Nevertheless, it is fragile, and failure results in a miscompile. This
verification pass checks that all (reachable) counter-based branches are
dominated by a loop mtctr instruction, and that no instructions in between
clobber the counter register. If these conditions are not satisfied, then an
ICE will be triggered.
In short, this is to help us sleep better at night.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182295 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
PowerPC has a conditional branch to the link register (return) instruction: BCLR.
This should be used any time when we'd otherwise have a conditional branch to a
return. This adds a small pass, PPCEarlyReturn, which runs just prior to the
branch selection pass (and, importantly, after block placement) to generate
these conditional returns when possible. It will also eliminate unconditional
branches to returns (these happen rarely; most of the time these have already
been tail duplicated by the time PPCEarlyReturn is invoked). This is a nice
optimization for small functions that do not maintain a stack frame.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179026 91177308-0d34-0410-b5e6-96231b3b80d8
As pointed out by Jakob, we don't need to maintain a separate
register-numbering table. Instead we should let TableGen generate the table for
us from the information (already present) in PPCRegisterInfo.td.
TRI->getEncodingValue is now used to access register-encoding values.
No functionality change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178067 91177308-0d34-0410-b5e6-96231b3b80d8
This provides a place to add customized operation cost information and
control some other target-specific IR-level transformations.
The only non-trivial logic in this checkin assigns a higher cost to
unaligned loads and stores (covered by the included test case).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@173520 91177308-0d34-0410-b5e6-96231b3b80d8
on 64-bit PowerPC ELF.
The patch includes code to handle external assembly and MC output with the
integrated assembler. It intentionally does not support the "old" JIT.
For the initial-exec TLS model, the ABI requires the following to calculate
the address of external thread-local variable x:
Code sequence Relocation Symbol
ld 9,x@got@tprel(2) R_PPC64_GOT_TPREL16_DS x
add 9,9,x@tls R_PPC64_TLS x
The register 9 is arbitrary here. The linker will replace x@got@tprel
with the offset relative to the thread pointer to the generated GOT
entry for symbol x. It will replace x@tls with the thread-pointer
register (13).
The two test cases verify correct assembly output and relocation output
as just described.
PowerPC-specific selection node variants are added for the two
instructions above: LD_GOT_TPREL and ADD_TLS. These are inserted
when an initial-exec global variable is encountered by
PPCTargetLowering::LowerGlobalTLSAddress(), and later lowered to
machine instructions LDgotTPREL and ADD8TLS. LDgotTPREL is a pseudo
that uses the same LDrs support added for medium code model's LDtocL,
with a different relocation type.
The rest of the processing is straightforward.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169281 91177308-0d34-0410-b5e6-96231b3b80d8
This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon
pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are
no longer otherwise used. Also, invalid preheader DebugLoc is not used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158204 91177308-0d34-0410-b5e6-96231b3b80d8
and MCSubtargetInfo.
- Added methods to update subtarget features (used when targets automatically
detect subtarget features or switch modes).
- Teach X86Subtarget to update MCSubtargetInfo features bits since the
MCSubtargetInfo layer can be shared with other modules.
- These fixes .code 16 / .code 32 support since mode switch is updated in
MCSubtargetInfo so MC code emitter can do the right thing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134884 91177308-0d34-0410-b5e6-96231b3b80d8
VK_PPC_{HA,LO}16 into darwin and gas variants.
Darwin wants {ha,lo}16(symbol) while gnu as wants symbol@{ha,l}.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132802 91177308-0d34-0410-b5e6-96231b3b80d8
directly on the mac. This is very early, doesn't support relocations and
has a terrible hack to avoid .machine from being printed, but despite
that it generates an bitwise-identical-to-cctools .o file for stuff like
this:
define i32 @test() nounwind { ret i32 42 }
I don't plan to continue pushing this forward, but if anyone else was
interested in doing it, it should be really straight-forward.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119136 91177308-0d34-0410-b5e6-96231b3b80d8
different ways. Add $non_lazy_ptr support, and proper lowering for
global values.
Now all the ppc regression tests pass with the new instruction printer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119106 91177308-0d34-0410-b5e6-96231b3b80d8
nodes to indicate when ha16/lo16 modifiers should be used. This lets
us pass PowerPC/indirectbr.ll.
The one annoying thing about this patch is that the MCSymbolExpr isn't
expressive enough to represent ha16(label1-label2) which we need on
PowerPC. I have a terrible hack in the meantime, but this will have
to be revisited at some point.
Last major conversion item left is global variable references.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119105 91177308-0d34-0410-b5e6-96231b3b80d8
and have isel apply to to call operands as required. This allows
us to get $stub suffixes on label references on ppc/tiger with the
new instprinter, fixing two tests. Only 2 to go.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119093 91177308-0d34-0410-b5e6-96231b3b80d8
--- Reverse-merging r75799 into '.':
U test/Analysis/PointerTracking
U include/llvm/Target/TargetMachineRegistry.h
U include/llvm/Target/TargetMachine.h
U include/llvm/Target/TargetRegistry.h
U include/llvm/Target/TargetSelect.h
U tools/lto/LTOCodeGenerator.cpp
U tools/lto/LTOModule.cpp
U tools/llc/llc.cpp
U lib/Target/PowerPC/PPCTargetMachine.h
U lib/Target/PowerPC/AsmPrinter/PPCAsmPrinter.cpp
U lib/Target/PowerPC/PPCTargetMachine.cpp
U lib/Target/PowerPC/PPC.h
U lib/Target/ARM/ARMTargetMachine.cpp
U lib/Target/ARM/AsmPrinter/ARMAsmPrinter.cpp
U lib/Target/ARM/ARMTargetMachine.h
U lib/Target/ARM/ARM.h
U lib/Target/XCore/XCoreTargetMachine.cpp
U lib/Target/XCore/XCoreTargetMachine.h
U lib/Target/PIC16/PIC16TargetMachine.cpp
U lib/Target/PIC16/PIC16TargetMachine.h
U lib/Target/Alpha/AsmPrinter/AlphaAsmPrinter.cpp
U lib/Target/Alpha/AlphaTargetMachine.cpp
U lib/Target/Alpha/AlphaTargetMachine.h
U lib/Target/X86/X86TargetMachine.h
U lib/Target/X86/X86.h
U lib/Target/X86/AsmPrinter/X86ATTAsmPrinter.h
U lib/Target/X86/AsmPrinter/X86AsmPrinter.cpp
U lib/Target/X86/AsmPrinter/X86IntelAsmPrinter.h
U lib/Target/X86/X86TargetMachine.cpp
U lib/Target/MSP430/MSP430TargetMachine.cpp
U lib/Target/MSP430/MSP430TargetMachine.h
U lib/Target/CppBackend/CPPTargetMachine.h
U lib/Target/CppBackend/CPPBackend.cpp
U lib/Target/CBackend/CTargetMachine.h
U lib/Target/CBackend/CBackend.cpp
U lib/Target/TargetMachine.cpp
U lib/Target/IA64/IA64TargetMachine.cpp
U lib/Target/IA64/AsmPrinter/IA64AsmPrinter.cpp
U lib/Target/IA64/IA64TargetMachine.h
U lib/Target/IA64/IA64.h
U lib/Target/MSIL/MSILWriter.cpp
U lib/Target/CellSPU/SPUTargetMachine.h
U lib/Target/CellSPU/SPU.h
U lib/Target/CellSPU/AsmPrinter/SPUAsmPrinter.cpp
U lib/Target/CellSPU/SPUTargetMachine.cpp
U lib/Target/Mips/AsmPrinter/MipsAsmPrinter.cpp
U lib/Target/Mips/MipsTargetMachine.cpp
U lib/Target/Mips/MipsTargetMachine.h
U lib/Target/Mips/Mips.h
U lib/Target/Sparc/AsmPrinter/SparcAsmPrinter.cpp
U lib/Target/Sparc/SparcTargetMachine.cpp
U lib/Target/Sparc/SparcTargetMachine.h
U lib/ExecutionEngine/JIT/TargetSelect.cpp
U lib/Support/TargetRegistry.cpp
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75820 91177308-0d34-0410-b5e6-96231b3b80d8
- This more or less amounts to a revert of r65379. I'm curious to know what
happened that caused this variable to become unused.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@74579 91177308-0d34-0410-b5e6-96231b3b80d8
Massive check in. This changes the "-fast" flag to "-O#" in llc. If you want to
use the old behavior, the flag is -O0. This change allows for finer-grained
control over which optimizations are run at different -O levels.
Most of this work was pretty mechanical. The majority of the fixes came from
verifying that a "fast" variable wasn't used anymore. The JIT still uses a
"Fast" flag. I'll change the JIT with a follow-up patch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70343 91177308-0d34-0410-b5e6-96231b3b80d8
use the old behavior, the flag is -O0. This change allows for finer-grained
control over which optimizations are run at different -O levels.
Most of this work was pretty mechanical. The majority of the fixes came from
verifying that a "fast" variable wasn't used anymore. The JIT still uses a
"Fast" flag. I'm not 100% sure if it's necessary to change it there...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70270 91177308-0d34-0410-b5e6-96231b3b80d8
them are generic changes.
- Use the "fast" flag that's already being passed into the asm printers instead
of shoving it into the DwarfWriter.
- Instead of calling "MI->getParent()->getParent()" for every MI, set the
machine function when calling "runOnMachineFunction" in the asm printers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@65379 91177308-0d34-0410-b5e6-96231b3b80d8