1. Computer Architecture Lecture 7 Compiler Considerations and Optimizations

2. Structure of Recent Compilers Front End Transform Language to Common Intermediate Form Note: Only few companies make front for C. Source code for C++ Front end is about 30 times bigger than C. Most Front down convert C++ to C before compilation. High Level Optimization High Level Loop Optimization Example: Procedure In-lining (Lang Dep., Machine Ind.) Global Optimization Global and Local Optimization and register allocation (Small Lang Dep., Small Machine dep.) Code Generation Detailed Instruction Selection and machine dependent optimization (No Lang Dep., Highly Machine Dep.)

3. Compiler Prime Target Program Correctness Speed Compilation Time? Phases of compilers help write bug-free code

4. Optimizations High-level Local (Basic Block) Global (across branches) Register Allocation, Live Range Analysis Processor Dependent

5. Optimization Names Procedure Integration Common Sub-expression Elimination/Dead Code Elimination A = b+ c ;dead code eliminated, no subsequent use of b+c A = x+ y Similarly if a procedure does not return a value and uses only local variables will be eliminated. (Test this in VC++) Constant Propagation: A variable used as constant. (Constants aren’t, Variable Won’t. Osborn’s Law) Global Sub-expression Elimination Copy Propagation (a = b, a will be replaced by b) Code Motion (A code that does not change with index in a loop will be moved out of the loop.) Induction Variable Elimination (A = A + 5 in a loop that runs n times will be replaced with A = A + 5 * n and moved out of loop, if A is not used,) Strength Reduction (Multiply replaced with shift and add if possible, A*25 + b*25 will be replaced with (A+B) * 25 ) Pipeline Scheduling Branch Optimization

6. Problems with Pointers A = 5; p = x+y; *p = 9 (only programmer knows &A = p) Compiler cannot assign a register

7. Architecture Help Provide Orthogonality The Operations, The Data Types, The Addressing Modes, The Register Functions should be orthogonal Simplify Trade-offs between alternatives (With caches and pipelining, trade-offs have become very complex) For Example: Most difficult one in register-memory architecture: How many times a variable is referenced before it is assigned a register. Provide Instructions to Bind Variables with Constants Most SIMD kernels are hand-coded as no compiler support

8. Hand-Coded VS Compiler Generated On TMS320C6203 (VLIW CPU) (reported May 2000) EEMBC Telecom Kernels Ratio of Execution Time (Compiler/Hand Written) Ratio of Code Size (Compiler/Hand Written) Convolution Encoder44.00.5 Fixed Point Complex FFT 13.51.0 Viterbi GSM Decoder13.00.7 Fixed Point Bit Allocation 7.01.4 Auto-correlation1.80.7

9. Basic Compiler Techniques Basic Pipelining Static Loop Unrolling Example: Instruction Producing Result Instruction Using Result Latency in CC FP ALU 3 Store2 LoadFP ALU1 FP LoadFP Store0

10. Example (Contd…) Loop: L.D F0, 0(R1) ADD.D F4,F0,F2 S.D F4, 0(R1) DADDUI R1,R1, #-8 BNEQ R1,R2, Loop

11. Example (Without Scheduling) Loop: L.D F0, 0(R1) stall ;LUD ADD.D F4,F0,F2 stall S.D F4, 0(R1) DADDUI R1,R1, #-8 stall BNEQ R1,R2, Loop stall ;Successor flushed Total 10cc

12. Example (With Scheduling) Loop: L.D F0, 0(R1) DADDUI R1,R1, #-8 ADD.D F4,F0,F2 stall BNEQ R1,R2, Loop S.D F4, 8(R1) ;delay slot Total 6cc (3 for data, 3 overhead)

13. Example (Static Loop Unrolling 4 times ) Loop: L.D F0, 0(R1) L.D F6, -8(R1) L.D F10, -16(R1) L.D F14, -24(R1) ADD.D F4,F0,F2 ADD.D F8,F6,F2 ADD.D F12,F10,F2 ADD.D F16,F14,F2 S.D F4, 0(R1) S.D F8, -8(R1) DADDUI R1,R1, #-32 S.D F12, 16(R1) BNEQ R1,R2, Loop S.D F16, 8(R1) ; Delay slot Total 3.5cc per element Compiler Considerations: 1.Use of delay slot 2.Loop level independence 3.Register Assignment 4.Proper Loop Adjustment

14. Example (Static Dual Issue, 1 Int and 1 FP/CC) Loop: L.D F0, 0(R1) L.D F6, -8(R1) L.D F10, -16(R1) ADD.D F4,F0,F2 L.D F14, -32(R1) ADD.D F8,F6,F2 L.D F18, -36(R1) ADD.D F12,F10,F2 S.D F4, 0(R1) ADD.D F16,F14,F2 S.D F8, -8(R1) ADD.D F20,F18,F2 S.D F12, -16(R1) DADDUI R1,R1, #-40 S.D F16, 16(R1) BNEQ R1,R2, Loop S.D F20, 8(R1) ; Delay slot Total 2.4cc per element LUD

15. VLIW Compiler formats issue packets Compiler ensures that dependencies are not present 64 to 200-bit long instructions

16. Example (VLIW, 1 Int, 2 FP, 2 LD/ST /CC 5-slots) Mem 1 SlotMem 2 SlotFP 1 SlotFP 2 SlotInt/ Branch L.D F0, 0(R1)L.D F6, -8(R1) L.D F10, -16(R1)L.D F14, -24(R1) L.D F18, -36(R1)L.D F22, -40(R1) ADD.D F4,F0,F2ADD.D F8,F6,F2 L.D F26, -48(R1)ADD.D F12,F10,F2 ADD.D F16,F14,F2 ADD.D F20,F18,F2ADD.D F24,F12,F2 S.D F4, 0(R1)S.D F8, -8(R1) ADD.D F28,F26,F2 S.D F12, -16(R1) S.D F16, -24(R1) DADDUI R1,R1, #-56 S.D F20, 24(R1) S.D F24, 16(R1) S.D F28, 8(R1)BNEQ R1,R2, Loop 1.29cc per element, 23 slots used out of potential 45

17. Loop Level Parallelism Loop Carried Dependence: Data calculated in one loop iteration is required in the next loop. A Parallel Loop For (I = 1000; I > 0; I = i-1) x[i] = x[i] + s

18. Example For (i = 1; i <= 100; i = i+1) { A[i+1] = A[i] + + C[i]; B[i+1] = B[i] + + A[i+1]; } Dependences?

19. Example 2 Make the following loop parallel. For (i = 1; i <= 100; i = i+1) { A[i] = A[i] + + B[i]; B[i+1] = C[i] + + D[i]; }

20. The GCD Test Loop stores in a  j + b and later fetches from c  k + d. Sufficient test is that if loop carried dependence exits then GCD(c,a) must integer divide (d-b) (no remainder). For (i = 1; i <= 100; i = i+1) x(2*i+3] = x[2*i] *5 This test ignores loop bounds.

21. Example 2 Use renaming to find ILP For (i = 1; i <= 100; i = i+1) { Y[i] = X[i] /c1 X[i] = X[i] +c2 Z[i] = Y[i] + c3 Y[i] = c4 - Y[i] /c }

22. Other techniques Addi R1, R2, # 4 To Addi R1, R2, # 8;copy Propagation And Add R1, R2, R3 Add R2, R1, R5 Addi R7, R2, R8 ;(tree height reduction) Sum = sum + x[i] Sum = (sum + x[1]) + ( x[2] + x[3]) + (x[4]+x[5]) ;recurrence optimization