1. Squish-DSP Application of a Project Management Tool to manage low-level DSP processor resources M. Smith, University of Calgary, Canada smithmr @ ucalgary.ca

2. Squish-DSP Tool smithmr@ucalgary.ca 2/28 Series of Talks and Workshops CACHE-DSP – Talk on a simple process tool to identify cache conflicts in DSP code. SQUISH-DSP – Talk on using a project management tool to automate identification of parallel DSP processor instructions. SHARC Ecology 101 – Workshop showing how to systematically write parallel 2106X code. SHARC Ecology 201 – Workshop on SQUISH-DSP and CACHE-DSP tools.

3. Squish-DSP Tool smithmr@ucalgary.ca 3/28 Scope of Talk Overview of hand optimization of code Paradigm shift in microprocessor resource scheduling Project Management Tool Application Translating ‘microprocessor’ language into a ‘business’ format Examples and limitations Better optimization from VisualDSP code Future directions

4. Squish-DSP Tool smithmr@ucalgary.ca 4/28 Standard “C” code void Convert(float *temperature, int N) { int count; for (count = 0; count < N; count++) { *temperature = (*temperature) * 9 / 5 + 32; temperature++ }

5. Squish-DSP Tool smithmr@ucalgary.ca 5/28 2106X-style load/store “C” code void Convert( register float *temperature, register int N ) { register int count; register float *pt = temperature; // Ireg <- Dreg register float scratch; for (count = 0; count < N; count++) { scratch = *pt; scratch = scratch * (9 / 5); scratch = scratch + 32; // Order of Ops *pt = scratch; pt++; }

6. Squish-DSP Tool smithmr@ucalgary.ca 6/28 Check on required register use #define count scratchR1 #define pt scratchDMpt #define scratchF2 F2 LCNTR = INPAR2, DO LOOP_END UNTIL LDE: scratchF2 = dm(pt, zeroDM); Any special requirements here on F2?? // INPAR1 (R4) is dead -- can reuse #define constantF4 F4// Must be float constantF4 = 1.8; scratchF2 = scratchF2 * constantF4 Fn = F(0,1,2 or 3) * F(4,5,6 or 7), #define F0_32 F0// Must be float F0_32 = 32.0; scratchF2 = scratchF2 + F0_32; Fm = F(8, 9, 10 or 11) + F(12, 13, 14 or 15) LOOP_END:dm(pt, plus1DM) = scratchF2;

7. Squish-DSP Tool smithmr@ucalgary.ca 7/28 Resource Chart -- Basic code

8. Squish-DSP Tool smithmr@ucalgary.ca 8/28 Unroll the loop -- 5 times here

9. Squish-DSP Tool smithmr@ucalgary.ca 9/28 Parallelism causes Register/Resource Conflicts SRC DEST

10. Squish-DSP Tool smithmr@ucalgary.ca 10/28 c Unroll the loop a bit more

11. Squish-DSP Tool smithmr@ucalgary.ca 11/28 Final code version

12. Squish-DSP Tool smithmr@ucalgary.ca 12/28 Real Life is not made up of ‘short loops’ Probably using DSP-intelligent compiler as a starting point Longer loops -- more tasks to make parallel Many different opportunities for task ordering Complicated resource management and register dependency issues Need a tool to help get the product ‘out the door’

13. Squish-DSP Tool smithmr@ucalgary.ca 13/28 Business Management Tool One evening went looking for a ‘tree’ program to manage the scheduling of microprocessor resources. In frustration, decided to take the 2106X tasks and put them into Microsoft Project. By mistake, found that I had developed a very useful microprocessor management tool, especially with the MS Project GUI! Question -- how to get it to function in a systematic manner?

14. Squish-DSP Tool smithmr@ucalgary.ca 14/28 MS Project -- 21XXX processor Requires a paradigm shift Business project concept -- One person can’t be doing two tasks in the same time slot. Becomes one data bus can’t be transferring two data items at same time Handled by identifying the ‘processor resources’ needed to complete each ‘basic task’.

15. Squish-DSP Tool smithmr@ucalgary.ca 15/28 MS Project -- 21XXX processor Business project concept. If you delay building a wall (Task A), then you must delay painting it (Task B) HOWEVER If you build the wall earlier, you could paint it earlier, but you don’t have to. Might make more sense to delay Task B so that Task C can be done earlier since doing Task C allows Task D to be completed in parallel with Task B so that the whole project is finished earlier.

16. Squish-DSP Tool smithmr@ucalgary.ca 16/28 Simple Example 1) F6 = dm(I4, M4); 10) F1 = F2 * F4, F8 = F8 + F12, F12 = pm(I12, M12); 16) F5 = F3 * F6, F8 = F8 + F12, F12 = pm(I12, M12); Might be able to move Task 1 in parallel with any instruction 2 through 15 BUT not in parallel with 16 If Task 10 moves earlier, so can Task 16, BUT not before Task 10 In Task 10 ‘F12=….’ can be made parallel with ‘F6=….’, BUT Task 10 ‘F8=….’ can’t!

17. Squish-DSP Tool smithmr@ucalgary.ca 17/28 SquishDSP -- parser 1) F6 = dm(I4, M4); 10) F1 = F2 * F4, F8 = F8 + F12, F12 = pm(I12, M12); 16) F5 = F3 * F6, F8 = F8 + F12, F12 = pm(I12, M12); Task 16 split into 3 atomic tasks F12 = pm(I12, M12) -- PMBUS resource, must come after ‘F12=…’ from Task 10, and after ‘F8=…’ in current Task F8 = F8 + F12 -- ALU resource, must come after ‘F8=…’ and ‘F12=…’ from Task 10 F5 = F3 * F6 -- MULTIPLIER resource, must come after ‘F6=…’ from Task 1

18. Squish-DSP Tool smithmr@ucalgary.ca 18/28 Preparation for Microsoft Project.asm Code broken up into sub-tasks with intra and inter dependencies recognized Reformatted as Microsoft Project Text file Rescheduled within Microsoft Project, either automatically or using GUI interface Reformatted as.asm code with increased parallelism

19. Squish-DSP Tool smithmr@ucalgary.ca 19/28 Example GUI screen capture INSTR. Broken into ATOMIC TASKS ATOMIC TASKS showing RESOURCE and DEPENDENCIES ATOMIC TASKS with RESOURCE CONFLICTS

20. Squish-DSP Tool smithmr@ucalgary.ca 20/28 Task scheduling after ‘LEVELING’

21. Squish-DSP Tool smithmr@ucalgary.ca 21/28 Initial ‘C’ code

22. Squish-DSP Tool smithmr@ucalgary.ca 22/28 Code from ‘Visual-DSP’ VisualDSP unrolled loop 3 times

23. Squish-DSP Tool smithmr@ucalgary.ca 23/28 Code from SQUISH-DSP 12 VisualDSP cycles squished to 8

24. Squish-DSP Tool smithmr@ucalgary.ca 24/28 Final version of code (loop change)

25. Squish-DSP Tool smithmr@ucalgary.ca 25/28 Final SQUISH 12 VisualDSP cycles squished to 6

26. Squish-DSP Tool smithmr@ucalgary.ca 26/28 Advantages and Limitations Current version intended to handle the inner critical loop of algorithm Not handling ‘Cache’ conflicts Not optimized for instructions in delay slots in jumps and conditional jumps Not optimized for multiple DAG delays e.g. I4 = …. ; DM(I4, M2) = ; I5 =… Moving to ‘task profile management’ macros with Primavera PV3 Tool

27. Squish-DSP Tool smithmr@ucalgary.ca 27/28 Conclusion SquishDSP is a prototype scheduling tool to identify and reschedule microprocessor resource operations in parallel Already useful in current form for ‘inner DSP loops’ Microsoft Project used for concept work but Primavera PV3 tool offers more long term promise

28. Squish-DSP Tool smithmr@ucalgary.ca 28/28 Acknowledgements Financial support of Natural Sciences and Engineering Research Council (NSERC) of Canada and University of Calgary Financial support from Analog Devices. Dr. Mike Smith is ADI University Professor 2001/2002 Future financial support from Alberta Provincial Government through Alberta Software Engineering Research Consortium (ASERC)