1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00

3 Commits

Author SHA1 Message Date
Kyungwoo Lee
b06062f9f0 [AArch64] Homogeneous Prolog and Epilog Size Optimization
Second land attempt. MachineVerifier DefRegState expensive check errors fixed.

Prologs and epilogs handle callee-save registers and tend to be irregular with
different immediate offsets that are not often handled by the MachineOutliner.
Commit D18619/a5335647d5e8 (combining stack operations) stretched irregularity
further.

This patch tries to emit homogeneous stores and loads with the same offset for
prologs and epilogs respectively. We have observed that this canonicalizes
(homogenizes) prologs and epilogs significantly and results in a greatly
increased chance of outlining, resulting in a code size reduction.

Despite the above results, there are still size wins to be had that the
MachineOutliner does not provide due to the special handling X30/LR. To handle
the LR case, his patch custom-outlines prologs and epilogs in place. It does
this by doing the following:

  * Injects HOM_Prolog and HOM_Epilog pseudo instructions during a Prolog and
    Epilog Injection Pass.
  * Lowers and optimizes said pseudos in a AArchLowerHomogneousPrologEpilog Pass.
  * Outlined helpers are created on demand. Identical helpers are merged by the linker.
  * An opt-in flag is introduced to enable this feature. Another threshold flag
    is also introduced to control the aggressiveness of outlining for application's need.

This reduced an average of 4% of code size on LLVM-TestSuite/CTMark targeting arm64/-Oz.

Differential Revision: https://reviews.llvm.org/D76570
2021-02-02 14:57:26 -08:00
Puyan Lotfi
293c83b00b Revert "[AArch64] Homogeneous Prolog and Epilog Size Optimization"
This reverts commit 0426be3df6180747bd68706db87a70580f064f0f.

Reverting due to some expensive-checks failures in tests.
2021-02-02 02:33:44 -05:00
Kyungwoo Lee
28c9f1933e [AArch64] Homogeneous Prolog and Epilog Size Optimization
Prologs and epilogs handle callee-save registers and tend to be irregular with
different immediate offsets that are not often handled by the MachineOutliner.
Commit D18619/a5335647d5e8 (combining stack operations) stretched irregularity
further.

This patch tries to emit homogeneous stores and loads with the same offset for
prologs and epilogs respectively. We have observed that this canonicalizes
(homogenizes) prologs and epilogs significantly and results in a greatly
increased chance of outlining, resulting in a code size reduction.

Despite the above results, there are still size wins to be had that the
MachineOutliner does not provide due to the special handling X30/LR. To handle
the LR case, his patch custom-outlines prologs and epilogs in place. It does
this by doing the following:

  * Injects HOM_Prolog and HOM_Epilog pseudo instructions during a Prolog and
    Epilog Injection Pass.
  * Lowers and optimizes said pseudos in a AArchLowerHomogneousPrologEpilog Pass.
  * Outlined helpers are created on demand. Identical helpers are merged by the linker.
  * An opt-in flag is introduced to enable this feature. Another threshold flag
    is also introduced to control the aggressiveness of outlining for application's need.

This reduced an average of 4% of code size on LLVM-TestSuite/CTMark targeting arm64/-Oz.

Differential Revision: https://reviews.llvm.org/D76570
2021-02-02 00:26:51 -05:00