[AutoFDO] Properly merge context-sensitive profile of inlinee back to outlined function

Summary:
When sample profile loader decides not to inline a previously inlined call-site, we adjust the profil

[AutoFDO] Properly merge context-sensitive profile of inlinee back to outlined function

Summary:
When sample profile loader decides not to inline a previously inlined call-site, we adjust the profile of outlined function simply by scaling up its profile counts by call-site count. This means the context-sensitive profile of that inlined instance will be thrown away. This commit try to keep context-sensitive profile for such cases:

- Instead of scaling outlined function's profile, we now properly merge the FunctionSamples of inlined instance into outlined function, including all recursively inlined profile.
- Instead of adjusting the profile for negative inline decision at the end of the sample profile loader pass, we do the profile merge right after processing each function. This change paired with top-down ordering of annotation/inline-replay (a separate diff) will make sure we recursively merge profile back before the profile is used for annotation and inline replay.

A new switch -sample-profile-merge-inlinee is added to enable the new profile merge for tuning. It should be the default behavior eventually.

Reviewers: wmi, davidxl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70653

show more ...

Revert "Revert r347596 "Support for inserting profile-directed cache prefetches""

Summary:
This reverts commit d8517b96dfbd42e6a8db33c50d1fa1e58e63fbb9.

Fix: correct the use of DenseMap.

Reviewer

Revert "Revert r347596 "Support for inserting profile-directed cache prefetches""

Summary:
This reverts commit d8517b96dfbd42e6a8db33c50d1fa1e58e63fbb9.

Fix: correct the use of DenseMap.

Reviewers: davidxl, hans, wmi

Reviewed By: wmi

Subscribers: mgorny, eraman, llvm-commits

Differential Revision: https://reviews.llvm.org/D55088

llvm-svn: 347938

show more ...

Support for inserting profile-directed cache prefetches

Summary:
Support for profile-driven cache prefetching (X86)

This change is part of a larger system, consisting of a cache prefetches recommen

Support for inserting profile-directed cache prefetches

Summary:
Support for profile-driven cache prefetching (X86)

This change is part of a larger system, consisting of a cache prefetches recommender, create_llvm_prof (https://github.com/google/autofdo), and LLVM.

A proof of concept recommender is DynamoRIO's cache miss analyzer. It processes memory access traces obtained from a running binary and identifies patterns in cache misses. Based on them, it produces a csv file with recommendations. The expectation is that, by leveraging such recommendations, we can reduce the amount of clock cycles spent waiting for data from memory. A microbenchmark based on the DynamoRIO analyzer is available as a proof of concept: https://goo.gl/6TM2Xp.

The recommender makes prefetch recommendations in terms of:

* the binary offset of an instruction with a memory operand;
* a delta;
* and a type (nta, t0, t1, t2)

meaning: a prefetch of that type should be inserted right before the instrution at that binary offset, and the prefetch should be for an address delta away from the memory address the instruction will access.

For example:

0x400ab2,64,nta

and assuming the instruction at 0x400ab2 is:

movzbl (%rbx,%rdx,1),%edx

means that the recommender determined it would be beneficial for a prefetchnta instruction to be inserted right before this instruction, as such:

prefetchnta 0x40(%rbx,%rdx,1)
movzbl (%rbx, %rdx, 1), %edx

The workflow for prefetch cache instrumentation is as follows (the proof of concept script details these steps as well):

1. build binary, making sure -gmlt -fdebug-info-for-profiling is passed. The latter option will enable the X86DiscriminateMemOps pass, which ensures instructions with memory operands are uniquely identifiable (this causes ~2% size increase in total binary size due to the additional debug information).

2. collect memory traces, run analysis to obtain recommendations (see above-referenced DynamoRIO demo as a proof of concept).

3. use create_llvm_prof to convert recommendations to reference insertion locations in terms of debug info locations.

4. rebuild binary, using the exact same set of arguments used initially, to which -mllvm -prefetch-hints-file=<file> needs to be added, using the afdo file obtained at step 3.

Note that if sample profiling feedback-driven optimization is also desired, that happens before step 1 above. In this case, the sample profile afdo file that was used to produce the binary at step 1 must also be included in step 4.

The data needed by the compiler in order to identify prefetch insertion points is very similar to what is needed for sample profiles. For this reason, and given that the overall approach (memory tracing-based cache recommendation mechanisms) is under active development, we use the afdo format as a syntax for capturing this information. We avoid confusing semantics with sample profile afdo data by feeding the two types of information to the compiler through separate files and compiler flags. Should the approach prove successful, we can investigate improvements to this encoding mechanism.

Reviewers: davidxl, wmi, craig.topper

Reviewed By: davidxl, wmi, craig.topper

Subscribers: davide, danielcdh, mgorny, aprantl, eraman, JDevlieghere, llvm-commits

Differential Revision: https://reviews.llvm.org/D54052

llvm-svn: 347596

show more ...