Download:
|
by Huiyang Zhou, Matthew D. Jennings, Thomas M. Conte
http://www.tinker.ncsu.edu/symposia/lcpc01.ps
Add To MetaCart
Abstract:
Global scheduling in a treegion framework has been proposed to exploit instruction level parallelism (ILP) at compile time. A treegion is a single-entry / multiple-exit global scheduling scope that consists of basic blocks with control-flow that forms a tree. Because a treegion scope is nonlinear (includes multiple paths) it is distinguished from linear scopes such as traces or superblocks. Treegion scheduling has the capability of speeding up all possible paths within the scheduling scope. This paper presents a new global scheduling algorithm using treegions called Tree Traversal Scheduling (TTS). Efficient, incremental data-flow analysis in support of TTS is also presented. Performance results are compared to the scheduling of the linear regions that result from the decomposition of treegions. We refer to these resultant linear regions as linear treegions (LT) and consider them analogous to superblocks with the same amount of code expansion as the base treegion. Experimental results for TTS scheduling show a 35 % speedup compared to basic block (BB) scheduling and a 4 % speedup compared to LT scheduling. 1.
Citations
|
560
|
Trace scheduling: A technique for global microcode compaction
– Fisher
- 1981
|
|
134
|
Highly Concurrent Scalar Processing
– Hsu
- 1986
|
|
92
|
HPL PlayDoh Architecture Specification: Version 1.0
– Kathail, Schlansker, et al.
- 1994
|
|
44
|
Percolation scheduling: A parallel compilation technique
– Nicolau
- 1985
|
|
43
|
HPL-PD architecture specification: Version 1.1
– Kathail, Schlansker, et al.
- 2000
|
|
40
|
EPIC: Explicitly Parallel Instruction Computing
– Schlansker, Rau
|
|
32
|
Exploiting Instruction Level Parallelism in the Presence of Conditional Branches
– Mahlke
- 1995
|
|
31
|
Treegion scheduling for wide-issue processors
– Havanki, Banerjia, et al.
- 1998
|
|
28
|
Profile-Driven Instruction Level Parallel Scheduling with Applications to Super Blocks
– CHEKURI, JOHNSON, et al.
- 1996
|
|
21
|
Wavefront Scheduling: Path Based Data Representation and Scheduling of Subgraphs
– Bharadwaj, Menezes, et al.
- 1999
|
|
19
|
Treegion scheduling for highly parallel processors
– Havanki, Conte
- 1997
|
|
19
|
Speculative Hedge: Regulating Compile-Time Speculation Against Profile Variations
– DEITRICH, W-M
- 1996
|
|
15
|
Elcor’s Machine Description System: Version 3.0
– Aditya, Kathail, et al.
- 1998
|
|
11
|
Architectural support for compile-time speculation
– Smith
- 1994
|
|
10
|
Path prediction for high issue-rate processors
– Menezes, Sathaye, et al.
- 1997
|
|
10
|
Dynamic Branch Prediction for a VLIW Processor
– Hoogerbrugge
- 1997
|
|
9
|
The Superblock: An effective way for VLIW and superblock compilation.” The
– Hwu, Mahlke, et al.
- 1993
|
|
7
|
Sathaye, "Instruction fetch mechanisms for VLIW architectures with compressed encodings
– Conte, Banerjia, et al.
- 1996
|
|
3
|
Global code generation for instruction level parallelism
– Fisher
- 1993
|
|
2
|
Bringmann "Effective compiler support for predicated execution using the Hyperblock
– Mahlke, Lin, et al.
- 1992
|
