RFR: 8318446: C2: implement StoreNode::Ideal_merge_stores

[Roland Westrelin]

On Wed, 17 Jan 2024 14:44:26 GMT, Roland Westrelin <roland at openjdk.org> wrote:

>> This is a feature requiested by @RogerRiggs and @cl4es .
>> 
>> **Idea**
>> 
>> Merging multiple consecutive small stores (e.g. 8 byte stores) into larger stores (e.g. one long store) can lead to speedup. Recently, @cl4es and @RogerRiggs had to review a few PR's where people would try to get speedups by using Unsafe (e.g. `Unsafe.putLongUnaligned`), or ByteArrayLittleEndian (e.g. `ByteArrayLittleEndian.setLong`). They have asked if we can do such an optimization in C2, rather than in the Java library code, or even user code.
>> 
>> This patch here supports a few simple use-cases, like these:
>> 
>> Merge consecutive array stores, with constants. We can combine the separate constants into a larger constant:
>> https://github.com/openjdk/jdk/blob/adca9e220822884d95d73c7f070adeee2632130d/test/hotspot/jtreg/compiler/c2/TestMergeStores.java#L383-L395
>> 
>> Merge consecutive array stores, with a variable that was split (using shifts). We can essentially undo the splitting (i.e. shifting and truncation), and directly store the variable:
>> https://github.com/openjdk/jdk/blob/adca9e220822884d95d73c7f070adeee2632130d/test/hotspot/jtreg/compiler/c2/TestMergeStores.java#L444-L456
>> 
>> The idea is that this would allow the introduction of a very simple API, without any "heavy" dependencies (Unsafe or ByteArrayLittleEndian):
>> 
>> https://github.com/openjdk/jdk/blob/adca9e220822884d95d73c7f070adeee2632130d/test/hotspot/jtreg/compiler/c2/TestMergeStores.java#L327-L338
>> https://github.com/openjdk/jdk/blob/adca9e220822884d95d73c7f070adeee2632130d/test/hotspot/jtreg/compiler/c2/TestMergeStores.java#L467-L472
>> 
>> **Details**
>> 
>> This draft currently implements the optimization in an additional special IGVN phase:
>> https://github.com/openjdk/jdk/blob/adca9e220822884d95d73c7f070adeee2632130d/src/hotspot/share/opto/compile.cpp#L2479-L2485
>> 
>> We first collect all `StoreB|C|I`, and put them in the IGVN worklist (see `Compile::gather_nodes_for_merge_stores`). During IGVN, we call `StoreNode::Ideal_merge_stores` at the end (after all other optimizations) of `StoreNode::Ideal`. We essentially try to establish a chain of mergable stores:
>> 
>> https://github.com/openjdk/jdk/blob/adca9e220822884d95d73c7f070adeee2632130d/src/hotspot/share/opto/memnode.cpp#L2802-L2806
>> 
>> Mergable stores must have the same Opcode (implies they have the same element type and hence size). Further, mergable stores must have the same control (or be separated by only a RangeCheck). Further, they must either bot...
>
> So what happens to the range checks in this transformation?

> @rwestrel good question: I start at the "latest" store, and look up the memory graph, also bypassing RangeChecks. When I decide to merge the stores, I place them at the place of the "latest" store, so after the RangeChecks. Now you might wonder: what happens if we were to actually fail a RangeCheck? Answer: I only replace the "latest" store. All earlier ones might still survive igvn if they have other uses, such as in a uncommon-trap. But they will probably sink out into the uncommon-trap path, and away from the main path, in which we should hopefully only have the merged store.

Wouldn't the first store in a chain of 3 stores have a use at the 2nd and 3rd range checks and so wouldn't sink?

-------------

PR Comment: https://git.openjdk.org/jdk/pull/16245#issuecomment-1895973468