Retargeting Open64 to A RISC processor A Students Perspective

1
Retargeting Open64 to A RISC processor -- A
Students Perspective

• Author Huimin Cui
• Xiaobing Feng
• 2009.03

1
2
Motivation

• Retarget is of significance for Open64
• Good retarget-ability brings more targets
• more targets support brings more user.
• But there is no detailed manual
• To show how to retarget step by step, to let even
  a green-hand can do the porting.
• To give an overview of the performance just after
  retarget done.

2
3
Retarget Procedure

• Summarized a detailed procedure for future
  retarget
• File creation order
• Building order
• Listed all the files that require modification
• How to fix up some critical files

3
4
Retarget Procedure our methodology(1)

• 1st step
• Verify basic compiler issues,
• C Front-end
• IR transformation
• Code generation
• Simple Library Function Call
• Naïve HelloWorld

4
5
Retarget Procedure our methodology(2)

• 2nd step
• Verify ABI/CFlow
• Variations of HelloWorld
• Change Data types of parameters
• Add control-flow branch loop
• 3rd step
• Verify optimization FRAMEWORK
• -O0, -O2, -O3

6
Retarget Procedure our methodology(3)

• 4th step
• Further verify CG/optimizations/multiple
  procedures
• Stanford benchmark, -O0 to O3
• 5th step
• Verify c FE/loop optimizations
• Abstraction penalty benchmark, -O0 to O3

6
7
Retarget Proceduresome points

• In most cases, its easier to tailor the files
  from existing ones
• Make the compiler work, then make it perform
• Use debugging tools of isolation/tracing/ dumping

7
8
DiscussionEasy of Retarget

• Took a student 2 months
• Dealt with
• ISA
• ABI
• Code Generation
• Some machine-dependent functions
• Passed the benchmarks, (-O0 to O3)
• Stanford Benchmark
• Abstraction Penalty Benchmark
• Some applications from CPU2000, bzip2 mcf

8
9
DiscussionPerformance (1)

• NO machine-dependent performance tuning after
  retarget.
• competitive or better performance compared to a
  matured GCC-Mips compiler
• obvious performance improvement from O2 to O3,
  especially for C programs with higher
  abstraction levels.

9
10
DiscussionPerformance(2)
Performance of abstraction penalty, -O2 and
O3 The higher, the better
10
11
DiscussionPerformance(3)
Performance of Stanford Benchmark The lower, the
better
11
12
DiscussionPerformance(4)
Performance of bzip2 mcf
12
13
Suggestions

• Can the flags distributed in multiple files be
  merged into one file?
• Eg. Endianness
• Can some graphic tools be developed for view IR,
  flow, etc?

13
14
Summary

• A detailed retarget procedure (derived from Fred
  Chows document)
• Shared our methodology
• Discussed two retargeting issues
• Ease of retarget
• Performance
• Some suggestions

15
Questions Comments?
Thank you!

• please mail to huimin.cui_at_gmail.com

15