Commit Graph

47 Commits

Author SHA1 Message Date
Daniel Berlin 25db4f4141 Add range iterators for post order and inverse post order. Use them
llvm-svn: 235026
2015-04-15 17:41:42 +00:00
Eric Christopher 3d4276f053 The subtarget is cached on the MachineFunction. Access it directly.
llvm-svn: 227173
2015-01-27 07:31:29 +00:00
David Blaikie 70573dcd9f Update SetVector to rely on the underlying set's insert to return a pair<iterator, bool>
This is to be consistent with StringSet and ultimately with the standard
library's associative container insert function.

This lead to updating SmallSet::insert to return pair<iterator, bool>,
and then to update SmallPtrSet::insert to return pair<iterator, bool>,
and then to update all the existing users of those functions...

llvm-svn: 222334
2014-11-19 07:49:26 +00:00
Pete Cooper 1175945710 Change MCSchedModel to be a struct of statically initialized data.
This removes static initializers from the backends which generate this data, and also makes this struct match the other Tablegen generated structs in behaviour

Reviewed by Andy Trick and Chandler C

llvm-svn: 216919
2014-09-02 17:43:54 +00:00
Craig Topper e1d1294853 Simplify creation of a bunch of ArrayRefs by using None, makeArrayRef or just letting them be implicitly created.
llvm-svn: 216525
2014-08-27 05:25:25 +00:00
Eric Christopher fc6de428c8 Have MachineFunction cache a pointer to the subtarget to make lookups
shorter/easier and have the DAG use that to do the same lookup. This
can be used in the future for TargetMachine based caching lookups from
the MachineFunction easily.

Update the MIPS subtarget switching machinery to update this pointer
at the same time it runs.

llvm-svn: 214838
2014-08-05 02:39:49 +00:00
Eric Christopher d913448b38 Remove the TargetMachine forwards for TargetSubtargetInfo based
information and update all callers. No functional change.

llvm-svn: 214781
2014-08-04 21:25:23 +00:00
Gerolf Hoflehner 5e1207e54c MachineCombiner Pass for selecting faster instruction
sequence -  target independent framework

 When the DAGcombiner selects instruction sequences
 it could increase the critical path or resource len.

 For example, on arm64 there are multiply-accumulate instructions (madd,
 msub). If e.g. the equivalent  multiply-add sequence is not on the
 crictial path it makes sense to select it instead of  the combined,
 single accumulate instruction (madd/msub). The reason is that the
 conversion from add+mul to the madd could lengthen the critical path
 by the latency of the multiply.

 But the DAGCombiner would always combine and select the madd/msub
 instruction.

 This patch uses machine trace metrics to estimate critical path length
 and resource length of an original instruction sequence vs a combined
 instruction sequence and picks the faster code based on its estimates.

 This patch only commits the target independent framework that evaluates
 and selects code sequences. The machine instruction combiner is turned
 off for all targets and expected to evolve over time by gradually
 handling DAGCombiner pattern in the target specific code.

 This framework lays the groundwork for fixing
 rdar://16319955

llvm-svn: 214666
2014-08-03 21:35:39 +00:00
Alexey Samsonov f74bde6735 Convert more loops to range-based equivalents
llvm-svn: 207714
2014-04-30 22:17:38 +00:00
Chandler Carruth 1b9dde087e [Modules] Remove potential ODR violations by sinking the DEBUG_TYPE
define below all header includes in the lib/CodeGen/... tree. While the
current modules implementation doesn't check for this kind of ODR
violation yet, it is likely to grow support for it in the future. It
also removes one layer of macro pollution across all the included
headers.

Other sub-trees will follow.

llvm-svn: 206837
2014-04-22 02:02:50 +00:00
Craig Topper c0196b1b40 [C++11] More 'nullptr' conversion. In some cases just using a boolean check instead of comparing to nullptr.
llvm-svn: 206142
2014-04-14 00:51:57 +00:00
Benjamin Kramer 502b9e1d7f Retire llvm::array_endof in favor of non-member std::end.
While there make array_lengthof constexpr if we have support for it.

llvm-svn: 206112
2014-04-12 16:15:53 +00:00
Owen Anderson 16c6bf49b7 Phase 2 of the great MachineRegisterInfo cleanup. This time, we're changing
operator* on the by-operand iterators to return a MachineOperand& rather than
a MachineInstr&.  At this point they almost behave like normal iterators!

Again, this requires making some existing loops more verbose, but should pave
the way for the big range-based for-loop cleanups in the future.

llvm-svn: 203865
2014-03-13 23:12:04 +00:00
Craig Topper 4584cd54e3 [C++11] Add 'override' keyword to virtual methods that override their base class.
llvm-svn: 203220
2014-03-07 09:26:03 +00:00
Benjamin Kramer d6f1f84f51 [C++11] Replace llvm::tie with std::tie.
The old implementation is no longer needed in C++11.

llvm-svn: 202644
2014-03-02 13:30:33 +00:00
Andrew Trick de2109eb4c Machine Model: Add MicroOpBufferSize and resource BufferSize.
Replace the ill-defined MinLatency and ILPWindow properties with
with straightforward buffer sizes:
MCSchedMode::MicroOpBufferSize
MCProcResourceDesc::BufferSize

These can be used to more precisely model instruction execution if desired.

Disabled some misched tests temporarily. They'll be reenabled in a few commits.

llvm-svn: 184032
2013-06-15 04:49:57 +00:00
Andrew Trick 85058af650 Generalize the MachineTraceMetrics public API.
Naturally, we should be able to pass in extra instructions, not just
extra blocks.

llvm-svn: 180667
2013-04-27 03:54:20 +00:00
Jakob Stoklund Olesen aeb69a5481 Allow MachineTraceMetrics to be used when the model has no resources.
It it still possible to extract information from itineraries, for
example.

llvm-svn: 178582
2013-04-02 22:27:45 +00:00
Jakob Stoklund Olesen 3ca14772d0 Count processor resources individually in MachineTraceMetrics.
The new instruction scheduling models provide information about the
number of cycles consumed on each processor resource. This makes it
possible to estimate ILP more accurately than simply counting
instructions / issue width.

The functions getResourceDepth() and getResourceLength() now identify
the limiting processor resource, and return a cycle count based on that.

This gives more precise resource information, particularly in traces
that use one resource a lot more than others.

llvm-svn: 178553
2013-04-02 17:49:51 +00:00
Jakob Stoklund Olesen 299cedc7ca Rename isEarlierInSameTrace to isUsefulDominator.
In very rare cases caused by irreducible control flow, the dominating
block can have the same trace head without actually being part of the
trace.

As long as such a dominator still has valid instruction depths, it is OK
to use it for computing instruction depths.

Rename the function to avoid lying, and add a check that instruction
depths are computed for the dominator.

llvm-svn: 176668
2013-03-07 23:55:49 +00:00
Jakob Stoklund Olesen 965665bb48 Move MachineTraceMetrics.h into include/llvm/CodeGen.
Let targets use it.

llvm-svn: 172688
2013-01-17 01:06:04 +00:00
Chandler Carruth ed0881b2a6 Use the new script to sort the includes of every file under lib.
Sooooo many of these had incorrect or strange main module includes.
I have manually inspected all of these, and fixed the main module
include to be the nearest plausible thing I could find. If you own or
care about any of these source files, I encourage you to take some time
and check that these edits were sensible. I can't have broken anything
(I strictly added headers, and reordered them, never removed), but they
may not be the headers you'd really like to identify as containing the
API being implemented.

Many forward declarations and missing includes were added to a header
files to allow them to parse cleanly when included first. The main
module rule does in fact have its merits. =]

llvm-svn: 169131
2012-12-03 16:50:05 +00:00
Jakob Stoklund Olesen d0d7860f40 Pass an explicit operand number to addLiveIns.
Not all instructions define a virtual register in their first operand.
Specifically, INLINEASM has a different format.

<rdar://problem/12472811>

llvm-svn: 165721
2012-10-11 16:46:07 +00:00
Jakob Stoklund Olesen 9d1173a86e Don't crash on extra evil irreducible control flow.
When the CFG contains a loop with multiple entry blocks, the traces
computed by MachineTraceMetrics don't always have the same nice
properties. Loop back-edges are normally excluded from traces, but
MachineLoopInfo doesn't recognize loops with multiple entry blocks, so
those back-edges may be included.

Avoid asserting when that happens by adding an isEarlierInSameTrace()
function that accurately determines if a dominating block is part of the
same trace AND is above the currrent block in the trace.

llvm-svn: 165434
2012-10-08 22:06:44 +00:00
Jakob Stoklund Olesen 8982222917 Switch MachineTraceMetrics to the new TargetSchedModel interface.
llvm-svn: 165235
2012-10-04 17:30:40 +00:00
Jakob Stoklund Olesen a0042acd3b Give MachineTraceMetrics its own debug tag.
llvm-svn: 161712
2012-08-10 22:27:29 +00:00
Jakob Stoklund Olesen 3484420927 Add more trace query functions.
Trace::getResourceLength() computes the number of cycles required to
execute the trace when ignoring data dependencies. The number can be
compared to the critical path to estimate the trace ILP.

Trace::getPHIDepth() computes the data dependency depth of a PHI in a
trace successor that isn't necessarily part of the trace.

llvm-svn: 161711
2012-08-10 22:27:27 +00:00
Jakob Stoklund Olesen 0954d4199a Include loop-carried dependencies when computing instr heights.
When a trace ends with a back-edge, include PHIs in the loop header in
the height computations. This makes the critical path through a loop
more accurate by including the latencies of the last instructions in the
loop.

llvm-svn: 161688
2012-08-10 20:11:38 +00:00
Jakob Stoklund Olesen bf1ac4bdc3 Deal with irreducible control flow when building traces.
We filter out MachineLoop back-edges during the trace-building PO
traversals, but it is possible to have CFG cycles that aren't natural
loops, and MachineLoopInfo doesn't include such cycles.

Use a standard visited set to detect such CFG cycles, and completely
ignore them when picking traces.

llvm-svn: 161532
2012-08-08 22:12:01 +00:00
Jakob Stoklund Olesen 296448b293 Fix a couple of typos.
llvm-svn: 161437
2012-08-07 18:32:57 +00:00
Jakob Stoklund Olesen 75d9d5159e Add trace accessor methods, implement primitive if-conversion heuristic.
Compare the critical paths of the two traces through an if-conversion
candidate. If the difference is larger than the branch brediction
penalty, reject the if-conversion. If would never pay.

llvm-svn: 161433
2012-08-07 18:02:19 +00:00
Jakob Stoklund Olesen 5d30630e22 Compute the critical path length through a trace.
Whenever both instruction depths and instruction heights are known in a
block, it is possible to compute the length of the critical path as
max(depth+height) over the instructions in the block.

The stored live-in lists make it possible to accurately compute the
length of a critical path that bypasses the current (small) block.

llvm-svn: 161197
2012-08-02 18:45:54 +00:00
Jakob Stoklund Olesen 2db6b65330 Compute instruction heights through a trace.
The height on an instruction is the minimum number of cycles from the
instruction is issued to the end of the trace. Heights are computed for
all instructions in and below the trace center block.

The method for computing heights is different from the depth
computation. As we visit instructions in the trace bottom-up, heights of
used instructions are pushed upwards. This way, we avoid scanning long
use lists, looking for uses in the current trace.

At each basic block boundary, a list of live-in registers and their
minimum heights is saved in the trace block info. These live-in lists
are used when restarting depth computations on a trace that
converges with an already computed trace. They will also be used to
accurately compute the critical path length.

llvm-svn: 161138
2012-08-01 22:36:00 +00:00
Jakob Stoklund Olesen 5e19d35e9a Add DataDep constructors. Explicitly check SSA form.
llvm-svn: 161115
2012-08-01 16:02:59 +00:00
Jakob Stoklund Olesen 059e647c6d Compute instruction depths through the current trace.
Assuming infinite issue width, compute the earliest each instruction in
the trace can issue, when considering the latency of data dependencies.
The issue cycle is record as a 'depth' from the beginning of the trace.

This is half the computation required to find the length of the critical
path through the trace. Heights are next.

llvm-svn: 161074
2012-07-31 20:44:38 +00:00
Jakob Stoklund Olesen 1dfb101835 Rename CT -> MTM. MachineTraceMetrics is abbreviated MTM.
llvm-svn: 161072
2012-07-31 20:25:13 +00:00
Jakob Stoklund Olesen 68c2cd059e Avoid looking at stale data in verifyAnalysis().
llvm-svn: 161004
2012-07-30 23:15:12 +00:00
Jakob Stoklund Olesen c14cf57ba9 Allow traces to enter nested loops.
This lets traces include the final iteration of a nested loop above the
center block, and the first iteration of a nested loop below the center
block.

We still don't allow traces to contain backedges, and traces are
truncated where they would leave a loop, as seen from the center block.

llvm-svn: 161003
2012-07-30 23:15:10 +00:00
Jakob Stoklund Olesen f308c128ea Assert that all trace candidate blocks have been visited by the PO.
When computing a trace, all the candidates for pred/succ must have been
visited. Filter out back-edges first, though. The PO traversal ignores
them.

Thanks to Andy for spotting this in review.

llvm-svn: 160995
2012-07-30 21:10:27 +00:00
Jakob Stoklund Olesen a12a7d5f74 Hook into PassManager's analysis verification.
By overriding Pass::verifyAnalysis(), the pass contents will be verified
by the pass manager.

llvm-svn: 160994
2012-07-30 20:57:50 +00:00
Jakob Stoklund Olesen 7361846f32 Add MachineInstr::isTransient().
This is a cleaned up version of the isFree() function in
MachineTraceMetrics.cpp.

Transient instructions are very unlikely to produce any code in the
final output. Either because they get eliminated by RegisterCoalescing,
or because they are pseudo-instructions like labels and debug values.

llvm-svn: 160977
2012-07-30 18:34:14 +00:00
Jakob Stoklund Olesen 3df6c46fdd Add MachineTraceMetrics::verify().
This function verifies the consistency of cached data in the
MachineTraceMetrics analysis.

llvm-svn: 160976
2012-07-30 18:34:11 +00:00
Jakob Stoklund Olesen eb488fe165 Verify that the CFG hasn't changed during invalidate().
The MachineTraceMetrics analysis must be invalidated before modifying
the CFG. This will catch some of the violations of that rule.

llvm-svn: 160969
2012-07-30 17:36:49 +00:00
Jakob Stoklund Olesen 0563369755 Add more debug output to MachineTraceMetrics.
llvm-svn: 160905
2012-07-27 23:58:38 +00:00
Jakob Stoklund Olesen 1152202cc2 Keep track of the head and tail of the trace through each block.
This makes it possible to quickly detect blocks that are outside the
trace.

llvm-svn: 160904
2012-07-27 23:58:36 +00:00
Jakob Stoklund Olesen 35400b1dda Use an otherwise unused variable.
llvm-svn: 160798
2012-07-26 19:42:56 +00:00
Jakob Stoklund Olesen f9029fef2a Start scaffolding for a MachineTraceMetrics analysis pass.
This is still a work in progress.

Out-of-order CPUs usually execute instructions from multiple basic
blocks simultaneously, so it is necessary to look at longer traces when
estimating the performance effects of code transformations.

The MachineTraceMetrics analysis will pick a typical trace through a
given basic block and provide performance metrics for the trace. Metrics
will include:

- Instruction count through the trace.
- Issue count per functional unit.
- Critical path length, and per-instruction 'slack'.

These metrics can be used to determine the performance limiting factor
when executing the trace, and how it will be affected by a code
transformation.

Initially, this will be used by the early if-conversion pass.

llvm-svn: 160796
2012-07-26 18:38:11 +00:00