The previous situation where ATOMIC_LOAD_WHATEVER nodes were expanded
at MachineInstr emission time had grown to be extremely large and
involved, to account for the subtly different code needed for the
various flavours (8/16/32/64 bit, cmpxchg/add/minmax).
Moving this transformation into the IR clears up the code
substantially, and makes future optimisations much easier:
1. an atomicrmw followed by using the *new* value can be more
efficient. As an IR pass, simple CSE could handle this
efficiently.
2. Making use of cmpxchg success/failure orderings only has to be done
in one (simpler) place.
3. The common "cmpxchg; did we store?" idiom can be exposed to
optimisation.
I intend to gradually improve this situation within the ARM backend
and make sure there are no hidden issues before moving the code out
into CodeGen to be shared with (at least ARM64/AArch64, though I think
PPC & Mips could benefit too).
llvm-svn: 205525
ARM specific optimiztion, finding places in ARM machine code where 2 dmbs
follow one another, and eliminating one of them.
Patch by Reinoud Elhorst.
llvm-svn: 205409
a TargetMachine to construct (and thus isn't always available), to an
analysis group that supports layered implementations much like
AliasAnalysis does. This is a pretty massive change, with a few parts
that I was unable to easily separate (sorry), so I'll walk through it.
The first step of this conversion was to make TargetTransformInfo an
analysis group, and to sink the nonce implementations in
ScalarTargetTransformInfo and VectorTargetTranformInfo into
a NoTargetTransformInfo pass. This allows other passes to add a hard
requirement on TTI, and assume they will always get at least on
implementation.
The TargetTransformInfo analysis group leverages the delegation chaining
trick that AliasAnalysis uses, where the base class for the analysis
group delegates to the previous analysis *pass*, allowing all but tho
NoFoo analysis passes to only implement the parts of the interfaces they
support. It also introduces a new trick where each pass in the group
retains a pointer to the top-most pass that has been initialized. This
allows passes to implement one API in terms of another API and benefit
when some other pass above them in the stack has more precise results
for the second API.
The second step of this conversion is to create a pass that implements
the TargetTransformInfo analysis using the target-independent
abstractions in the code generator. This replaces the
ScalarTargetTransformImpl and VectorTargetTransformImpl classes in
lib/Target with a single pass in lib/CodeGen called
BasicTargetTransformInfo. This class actually provides most of the TTI
functionality, basing it upon the TargetLowering abstraction and other
information in the target independent code generator.
The third step of the conversion adds support to all TargetMachines to
register custom analysis passes. This allows building those passes with
access to TargetLowering or other target-specific classes, and it also
allows each target to customize the set of analysis passes desired in
the pass manager. The baseline LLVMTargetMachine implements this
interface to add the BasicTTI pass to the pass manager, and all of the
tools that want to support target-aware TTI passes call this routine on
whatever target machine they end up with to add the appropriate passes.
The fourth step of the conversion created target-specific TTI analysis
passes for the X86 and ARM backends. These passes contain the custom
logic that was previously in their extensions of the
ScalarTargetTransformInfo and VectorTargetTransformInfo interfaces.
I separated them into their own file, as now all of the interface bits
are private and they just expose a function to create the pass itself.
Then I extended these target machines to set up a custom set of analysis
passes, first adding BasicTTI as a fallback, and then adding their
customized TTI implementations.
The fourth step required logic that was shared between the target
independent layer and the specific targets to move to a different
interface, as they no longer derive from each other. As a consequence,
a helper functions were added to TargetLowering representing the common
logic needed both in the target implementation and the codegen
implementation of the TTI pass. While technically this is the only
change that could have been committed separately, it would have been
a nightmare to extract.
The final step of the conversion was just to delete all the old
boilerplate. This got rid of the ScalarTargetTransformInfo and
VectorTargetTransformInfo classes, all of the support in all of the
targets for producing instances of them, and all of the support in the
tools for manually constructing a pass based around them.
Now that TTI is a relatively normal analysis group, two things become
straightforward. First, we can sink it into lib/Analysis which is a more
natural layer for it to live. Second, clients of this interface can
depend on it *always* being available which will simplify their code and
behavior. These (and other) simplifications will follow in subsequent
commits, this one is clearly big enough.
Finally, I'm very aware that much of the comments and documentation
needs to be updated. As soon as I had this working, and plausibly well
commented, I wanted to get it committed and in front of the build bots.
I'll be doing a few passes over documentation later if it sticks.
Commits to update DragonEgg and Clang will be made presently.
llvm-svn: 171681
current IR-level pass.
The old SjLj EH pass has some problems, especially with the new EH model. Most
significantly, it violates some of the new restrictions the new model has. For
instance, the 'dispatch' table wants to jump to the landing pad, but we cannot
allow that because only an invoke's unwind edge can jump to a landing pad. This
requires us to mangle the code something awful. In addition, we need to keep the
now dead landingpad instructions around instead of CSE'ing them because the
DWARF emitter uses that information (they are dead because no control flow edge
will execute them - the control flow edge from an invoke's unwind is superceded
by the edge coming from the dispatch).
Basically, this pass belongs not at the IR level where SSA is king, but at the
code-gen level, where we have more flexibility.
llvm-svn: 140646
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.
llvm-svn: 134884
difficult on current ARM implementations for a few reasons.
1. Even though a single vmla has latency that is one cycle shorter than a pair
of vmul + vadd, a RAW hazard during the first (4? on Cortex-a8) can cause
additional pipeline stall. So it's frequently better to single codegen
vmul + vadd.
2. A vmla folowed by a vmul, vmadd, or vsub causes the second fp instruction to
stall for 4 cycles. We need to schedule them apart.
3. A vmla followed vmla is a special case. Obvious issuing back to back RAW
vmla + vmla is very bad. But this isn't ideal either:
vmul
vadd
vmla
Instead, we want to expand the second vmla:
vmla
vmul
vadd
Even with the 4 cycle vmul stall, the second sequence is still 2 cycles
faster.
Up to now, isel simply avoid codegen'ing fp vmla / vmls. This works well enough
but it isn't the optimial solution. This patch attempts to make it possible to
use vmla / vmls in cases where it is profitable.
A. Add missing isel predicates which cause vmla to be codegen'ed.
B. Make sure the fmul in (fadd (fmul)) has a single use. We don't want to
compute a fmul and a fmla.
C. Add additional isel checks for vmla, avoid cases where vmla is feeding into
fp instructions (except for the #3 exceptional case).
D. Add ARM hazard recognizer to model the vmla / vmls hazards.
E. Add a special pre-regalloc case to expand vmla / vmls when it's likely the
vmla / vmls will trigger one of the special hazards.
Work in progress, only A+B are enabled.
llvm-svn: 120960
the same condition, it's important to make sure they are scheduled together
to avoid forming multiple IT blocks. I'm adding a pre-regalloc pass that forms
IT blocks early (by re-scheduling instructions and split basic blocks) to
attempt to fix this. This is not turned on by default since I am not sure this
is the right fix.
Another issue is llvm selects are modeled as two-address conditional moves.
This can be very bad when the copies before the conditional moves are not
coalesced away. Teach IT formation pass to move the copies above the IT block
(when legal) to avoid breaking the IT block.
llvm-svn: 105669
load of a GV from constantpool and then add pc. It allows the code sequence to
be rematerializable so it would be hoisted by machine licm.
- Add a late pass to break these pseudo instructions into a number of real
instructions. Also move the code in Thumb2 IT pass that breaks up t2MOVi32imm
to this pass. This is done before post regalloc scheduling to allow the
scheduler to proper schedule these instructions. It also allow them to be
if-converted and shrunk by later passes.
llvm-svn: 86304
that have that constraint. This is currently just assigning a fixed set of
registers, and it only handles VLDn for n=2,3,4 with DPR registers.
I'm going to expand it to handle more operations next; we can make it smarter
once everything is working correctly.
llvm-svn: 78256
--- 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
llvm-svn: 75820
Tim Northover