A new idiom recognition framework for exploiting hardware-assist instructions

Abstract

Modern processors support hardware-assist instructions (such as TRT and TROT instructions on IBM zSeries) to accelerate certain functions such as delimiter search and character conversion. Such special instructions have often been used in high performance libraries, but they have not been exploited well in optimizing compilers except for some limited cases. We propose a new idiom recognition technique derived from a topological embedding algorithm [4] to detect idiom patterns in the input program more aggressively than in previous approaches. Our approach can detect a pattern even if the code segment does not exactly match the idiom. For example, we can detect a code segment that includes additional code within the idiom pattern. We implemented our new idiom recognition approach based on the Java Just-In-Time (JIT) compiler that is part of the J9 Java Virtual Machine, and we supported several important idioms for special hardware-assist instructions on the IBM zSeries and on some models of the IBM pSeries. To demonstrate the effectiveness of our technique, we performed two experiments. The first one is to see how many more patterns we can detect compared to the previous approach. The second one is to see how much performance improvement we can achieve over the previous approach. For the first experiment, we used the Java Compatibility Kit (JCK) API tests. For the second one we used IBM XML parser, SPECjvm98, and SPCjbb2000. In summary, relative to a baseline implementation using exact pattern matching, our algorithm converted 75% more loops in JCK tests. We also observed significant performance improvement of the XML parser by 64%, of SPECjvm98 by 1%, and of SPECjbb2000 by 2% on average on a z990. Finally, we observed the JIT compilation time increases by only 0.32% to 0.44%.

Idiom recognition framework using topological embedding

“…This section describes an important optimization after performing the idiom recognition. The earlier version of this article [Kawahito et al 2006] does not include this optimization. At the end of idiom recognition (as seen in Figure 3), instruction simplification can transform a complex instruction to a less complex instruction when the exact value is not needed as the output for the following instructions.…”

“…In addition, we use instruction simplification for the idiom recognition. The earlier version of this article [Kawahito et al 2006] did not include this optimization, but there are some cases in which additional analysis can improve the performance of the converted code by transforming the complex instruction to a less complex instruction by instruction simplification when only a range of the value, such as positiveness or negativeness, is needed. For example, the method compareTo in the String class returns the difference of the two character values of the input strings if they have different characters [Sun Corp. 2006].…”