Source Code Optimization Techniques for Data Flow Dominated Embedded SoftwareSpringer Science & Business Media, 2013. gada 19. marts - 226 lappuses This book focuses on source-to-source code transformations that remove addressing-related overhead present in most multimedia or signal processing application programs. This approach is complementary to existing compiler technology. What is particularly attractive about the transformation flow pre sented here is that its behavior is nearly independent of the target processor platform and the underlying compiler. Hence, the different source code trans formations developed here lead to impressive performance improvements on most existing processor architecture styles, ranging from RISCs like ARM7 or MIPS over Superscalars like Intel-Pentium, PowerPC, DEC-Alpha, Sun and HP, to VLIW DSPs like TI C6x and Philips TriMedia. The source code did not have to be modified between processors to obtain these results. Apart from the performance improvements, the estimated energy is also significantly reduced for a given application run. These results were not obtained for academic codes but for realistic and rep resentative applications, all selected from the multimedia domain. That shows the industrial relevance and importance of this research. At the same time, the scientific novelty and quality of the contributions have lead to several excellent papers that have been published in internationally renowned conferences like e. g. DATE. This book is hence of interest for academic researchers, both because of the overall description of the methodology and related work context and for the detailed descriptions of the compilation techniques and algorithms. |
Saturs
INTRODUCTION | 1 |
1 | 7 |
1 | 11 |
2 | 15 |
3 | 26 |
FUNDAMENTAL CONCEPTS FOR OPTIMIZATION | 31 |
5 | 37 |
1 | 38 |
8 | 78 |
13 | 84 |
20 | 113 |
ADVANCED CODE HOISTING | 119 |
ཙྱི | 120 |
6 | 126 |
12 | 134 |
RING BUFFER REPLACEMENT | 163 |
Citi izdevumi - Skatīt visu
Source Code Optimization Techniques for Data Flow Dominated Embedded Software Heiko Falk,Peter Marwedel Ierobežota priekšskatīšana - 2004 |
Source Code Optimization Techniques for Data Flow Dominated Embedded Software Heiko Falk,Peter Marwedel Priekšskatījums nav pieejams - 2014 |
Source Code Optimization Techniques for Data Flow Dominated Embedded Software Heiko Falk,Peter Marwedel Priekšskatījums nav pieejams - 2011 |
Bieži izmantoti vārdi un frāzes
advanced code hoisting ARM7 ARM7TDMI array cache misses chapter chromosome column common subexpression elimination compiler optimizations computation constraints control flow data cache data partitioning data reuse definition denotes DTSE else-part Energy Consumption finite union fitness function for-loops genetic algorithm global search space I-Fetch L1 I-Miss I-Miss L1 D-Fetch if_count if-statement executions if-statements in_pixels index variables individual innermost loop instruction pipeline Intel Pentium intermediate representation IR-C L1 I-Fetch L1 L1 I-Miss L1 leads live range loop bounds loop nest splitting loop unrolling loop-invariant code motion memory accesses memory hierarchy MIPS node number of executions occurrences optimization techniques original Benchmark Versions performed Pipeline and Cache reduced represents ring buffer replacement ring buffer scalarization runtimes satisfied scratchpad search space exploration source code optimization source code transformation speed-ups splitting-if structure SUIF Sun UltraSPARC syntax tree tion TriMedia UltraSPARC union of polytopes values Ym+1