1. Explaining issues with DCremoval( )
Common problems to avoid

2. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Tackled today
Testing the performance of the CPP version
First assembly version – using I-ALU operations – testing and timing
Details of the code
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

3. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Memory intensive Addition intensive
Loops for main code
FIFO implemented as circular buffer
Not as complex as FIR, but many of the same requirements
Easier to handle
You use same ideas in optimizing FIR over Labs 2 and 3
Two issues – speed and accuracy. Develop suitable tests for CPP code and check that various assembly language versions satisfy the same tests
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

4. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Call and return test
Basically – if the code gets here it is probably that we did not crash the system
I use a cut-and-paste approach to develop code variants. This test is (embarrassingly) useful.
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

5. Initially we expect the code to fail to work correctly
If the code works initially, then it is doing so by accident
Use
XF_CHECK_EQUAL( )
Expected to fail
NOTE: This test is just a “cut-and-paste” version of C++ test
with three changes of function name
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

6. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Timing test
Once
10 times
100 times
Normalized the timing tests to “process the function once”
Need to develop various other routines to make tests work -- DoNothing loop, run C++ and assembly code routines in a loop
May not be correctly performing timing – but gives initial concepts
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

7. Other functions needed to run the test
Do Nothing Careful – may be optimized to “nothing”
C++ function loop
J-ALU function loop
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

8. Use build failure information to determine assembly code function name
Required name for void DCremovalASM_JALU(int *, int *)
_DCremoval_JALU__FPiT1
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

9. Proper test run and exit – lib_prog_term
Yellow indicates that there are NO failures but some expected failures
All successes and failures shown in console window
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

10. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Quick look at the code
void DCremovalASM(int *, int *)
Setting up the static arrays
Defining and then setting pointers
Moving incoming parameters in FIFO
Summing the FIFO values
Performing (FAST) division
Returning the correct values
Updating the FIFO in preparation for next time this function is called – discarding oldest value, and “rippling” the FIFO to make the “newest” FIFO slot empty
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

11. Developing the assembly code static arrays – “section data1”
In later algorithms we will show that using multiple data sections in different parts of TigerSHARC memory allow us to bring in 256-bits of data per cycle
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

12. Developing the assembly code static arrays – “section data1”
2) .align 4;
Later will use ability to bring in 4 words (32-bits) of data at the same time.
Works best when the array starts on a 4 word boundary
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

13. Developing the assembly code static arrays – “section data1”
3) .var array[128];
The .var syntax allows declaring of “word” arrays. Other syntax for short int and byte arrays
NOTE: -- reused .align 4 before next array
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

14. Developing the assembly code static arrays – “section data1”
4) .var array[128];
Array is “static” – known in this file only – as we don’t globalize the name TRUE or FALSE?
KEY – switch between data and program memory is “really key”
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

15. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Define the (250) register names for code maintainability (and marking) ease
Actual static array declaration DEFINE pointers into arrays
DEFINE temps
DEFINE Inpars SET pointers into arrays
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

16. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Value into FIFO buffer
RISC processor LOAD and STORE architecture –
Use pointer value (came in J4) to read “left value” passed in by reference into a register
MIPS – like rather than CISC
Now place this value into last element of FIFO array (make sure that not one element out.
NOTE – BUFFERSIZE – 1 is converted BY ASSEMBLER and does not happen at run time
Using index with pre-modify offset – J2 is not changed
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

17. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Perform sum
Hardware loop 1
Set up an index i_J8 to be used as offset into
Array – note how this syntax follows C++
Set up LOOP COUNTER 0
Perform test and jumo
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

18. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Perform sum
Hardware loop 2
Set up LOOP COUNTER 0
Division by 128 is performed by shift (What did C++ do)
Note that with the I-ALU you can only shift by 1 bit (not a barrel shifter).
Perform test and jumo
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

19. Some obvious multiple instructions. Can they go wrong?
Note Add occurs whether the jump does or does not occur
Should this be a predicted or non-predicted jump
One shift too many?
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

20. Correcting INPARS and then updating the FIFO buffer
Adjust the INPARS remember int *
Update FIFO memory using load / store approach
SLOW
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

21. Adjust tests for expected success
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

22. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Run the tests
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

23. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Examine the timing
In “debug” mode, we are already “beating” the compiler”
Questions
Why is C++ slower? Is it doing something that us (in ignorance) don’t know we need to do?
What happens with “release mode”?
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

24. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Can you explain this 10% change in the results depending on how many tests?
Timing with all the tests
Timing Test only
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada

25. DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada
Tackled today
What are the basic characteristics of a DSP algorithm?
A near perfect “starting” example
DCRemoval( ) has many of the features of the FIR filters used in all the Labs
Testing the performance of the CPP version
First assembly version – using I-ALU operations – testing and timing
Code will be examined in more detail in the next lecture
2/23/2019
DC removal Lecture 1, M. Smith, ECE, University of Calgary, Canada