Replace std::exit with v3Global.exit, and make V3Error::vlAbort call
v3Global.shutdown. This gives us an opportunity to release resources to
facilitate leak checking even when exiting early on an error.
Note we still don't release most resources by default without
VL_LEAK_CHECKS, so there is no behaviour change there.
Add a new pass to split up (recursively):
foo = {l, r};
into the following, with the right indices, iff the concatenation
straddles a wide word boundary.
foo[_:_] = r;
foo[_:_] = l;
This eliminates more wide temporaries.
Another 23% speedup on VeeR EH2 high_perf. Also brings the predicted
stack size from 8M to 40k.
The DFG peephole pass converts all associative trees into right leaning,
which is good for simplifying pattern recognition, but can lead to an
excessive amount of wide intermediate results being constructed for
right leaning concatenations.
Add a new pass to balance concatenation trees by trying to:
- Create VL_EDATASIZE (32-bit) sub-terms, so words can then be packed
easily afterwards
- Try to ensure the operands of a concat are roughly the same width
within a concatenation tree. This does not yield the shortest tree,
but it ensures it has many sub-nodes that are small enough to fit into
machine registers.
This can eliminate a lot of wide intermediate results, which would need
temporaries, and also increases ILP within sub-expressions (assuming the
C compiler can't figure that out itself).
This is over 2x run-time speedup on the high_perf configuration of
VeeR EH2 (which you could arguably also get with -fno-dfg, but oh well).
Instead of carrying around MTask affinity from scheduling, compute it in
V3VariableOrder (where it is used), by tracing through the code. This
simplifies some code and has the benefit of handling variables
introduced after scheduling. It's worth a few % speed at run-time, and
the new implementation of V3VariableOrder is slightly more efficient,
though the speed/space is still dominated by the TSP sort.
V3Partition used to contain 2 conceptually separate set of algorithms
- The MTask partitioning/coarsening algorithm used by V3Order. This has
been moved to V3OrderParallel.cpp
- The lowering of AstExecGraph into per thread functions by packing
tasks into threads and creating additional code
(V3Partition::finalize). This has been moved to the new
V3ExecGraph.cpp
This patch is just code movement/rename with minimal fixes required to
do so.
With --stats, we will print DFG pattern combinations, one per line, as
S-expressions to new stat files, together with their frequency, to aid
discovery of new peephole patterns.
Geza Lore
Wilson Snyder
Krzysztof Sychla
Andrew Voznytsa
Bartłomiej Chmiel
Arkadiusz Kozdra
Szymon Gizler
Szymon Gizler
Krzysztof Bieganski
Todd Strader
Anthony Donlon
Mariusz Glebocki
Krzysztof Boroński
Krzysztof Boronski