Introduction to Silicon Programming in the TangramHaste language

1
Introduction to Silicon Programmingin the
Tangram/Haste language

• Material adapted from lectures by
• Prof.dr.ir Kees van Berkel
• Dr. Johan Lukkien
• Dr.ir. Ad Peeters
• at the Technical University of Eindhoven, the
  Netherlands

2
VLSI programming for

• Low costs
• introduce resource sharing.
• Low delay (high throughput)
• introduce parallelism.
• Low energy (low power)
• reduce activity

3
VLSI programming for high performance

• Keep it simple!!
• Make the analysis focus on bottlenecks
• Introduce parallelism expressions, commands,
  loops, pipelining
• Enable parallelism, by reducing dependencies such
  as resource sharing

4
Expression-level parallelism

• Examples
• balancing (vw)(xy) is faster than vwxy
• substitution zg(f(x)) is faster than y
  f(x) z g(y)
• carry-select adder
• carry-save multiplier

5
Command level parallelism

• If S2 does not depend on outcome of S1 thenS1
  S2 can be transformed into S1
  S2.(dependencies data, sharing,
  synchronization)
• This reduces computation time ?, unless ordering
  is enforced through external synchronization.
• ?(S1 S2 ) ?() ?(S1) ?(S2)
• ?(S1 S2 ) ? () max(?(S1), ?(S2))

6
Exposure of cmd-level parallelism

• Let S be a shorthand for forever do S od
• Assume S0 must precede S1 and S1 must precede S2
  How to speedup S0 S1 S2 ?
• S0 S1 S2
• loop unfolding S0 S1 S2 S0
• S0 does not depend on S1 S0 S1 (S2
  S0)

7
wagging

• a?x b!f(x)
• loop unrolling, renaming
• a?x b!f(x) a?y b!f(y)
• loop folding
• a?x b!f(x) a?y b!f(y) a?x
• ? increases slack by 1
• a?x (b!f(x) a?y) (b!f(y) a?x)

8
Parallel reads from REG file

• Let RF be a register file. Then x RFi
  y RFj cannot be parallelized. (Register
  files have a single read port.)
• Parallel read actions can be realized by doubling
  the register file z write and , RGj read

9
Pipelining in Tangram

• Compare three programs
• P0 a?x0 b!f2(f1(f0(x0)))
• P1 a?x0 x1 f0(x0) x2 f1(x1)
  b!f2(x2)
• P2 a?x0 a1!f0(x0) a1?x1
  a2!f1(x1) a2?x2 b!f2(x2)

10
Pipelining in Tangram (cntd)

• Output sequence b identical for P0, P1, and P2.
• P0 and P1 have same communication behavior P1
  is larger, slower, and warmer.
• P2 vs P1 similar in size, energy, and latency,
  but up to 3 times higher throughput, depending
  on (relative) complexity of f0, f1, f2.

11
A Processor Example DLX (Deluxe)

• (AMD 29K DECstation 3100 HP850 IBM801
  Intel i860 MIPS M/120A MIPS M/1000 Motorola
  88K RISC I SGI 4D/60 SPARCstation-1 Sun
  4/110 Sun-4/260) / 13
• DLX
• Other RISC examples include
  Cray-1,2,3, AMD2900, DEC
  Alpha, ARM.

12
DLX instruction formats
31 26, 25 21, 20 16, 15 11, 10
0
13
Example instructions
14
GCD in DLX assembler

• pre LW R1,4(R0) R1Mem40
• LW R2,8(R0) R2Mem80
• loop SUB R3,R1,R2 R3R1-R2
• BEQZ R3,exit if (R30) then PCexit
• SLT R4,R1,R2 R4(R1
• BEQZ R4,pos2 if (R40) then PCpos2
• pos1 SUB R2,R2,R1 R2R2-R1
• J loop PCloop
• pos2 SUB R1,R1,R2 R1R1-R2
• J loop PCloop
• exit SW 20(R0),R1 Mem200R1
• HLT

15
DLX interface, state
Instruction memory
Mem (Data memory)
address
address
r0
pc
r1
r2
DLX CPU
Reg
instruction
data
r/w
r31
clock
interrupt
16
DLX Moore machine(ignoring interrupts)

• ?Reg0,pc ? ?0,0?
• do ?MemRegrs1 immediate, pc, Regrd ?
• ? if SW ? Regrd fi
• , if J ? pc4offset
• BEQZ ? if Regrs0 ? pc4
  immediate Regrs0 ? pc4 fi
• else ? pc4
• fi
• , if LW ? Memrs1immediate
• ADD ? ALU(add, Regrs1, Regrs2)
• fi ?
• od

17
DLX 5-step sequential execution
IF
ID
EX
MM
WB
18
DLX pipelined execution
Time ? in clock cycles 1 2 3
4 5 6 7 8
...
Program execution ? instructions
19
DLX pipelined execution
Instruction Fetch
Inst.Decode
EXecute
Memory
Write Back
4
0?
pc
Instr. mem
Reg
Mem
20
DLX system organization
RAMaddrdatatoRAMdatafromRAM
ROMaddrROMdata
dlx()

systemboundary
rom()
ram()
filesRAMoutRAMin
system_dlx()
file gcd.bin
21
dlx0.ht

• include types.ht
• dlx0 export proc ( ROMaddr!chan adtype
• ROMdata?chan word
• RAMaddr!chan rwadtype datatoRAM!chan
  S30 datafromRAM?chan S30
• ) .
• begin
• RF ram array U5 of S30
• end

22
system_dlx0.ht

• include "dlx0.ht"
• dlx0 proc ( ROMaddr!chan adtype
• ROMdata?chan word
• RAMaddr!chan rwadtype datatoRAM!chan
  S30 datafromRAM?chan S30
• ) . import
• env_dlx4 main proc (
• ROMfile? chan word
• RAMinfile? chan S30
• RAMfile! chan S30 /
  /
• ) .
• begin
• next slide
• end

23
system_dlx0.ht main body

• begin
• ROMaddr chan adtype
• ROMdata chan word
• RAMaddr chan rwadtype
• datatoRAM chan S30
• datafromRAM chan S30
• ROMinterface proc() . begin .. end
• RAMinterface proc() . begin .. end
• initialise() ROMinterface()
  RAMinterface() dlx0( ROMaddr, ROMdata,
  RAMaddr, datatoRAM, datafromRAM )
• end

24
script

• htcomp system_dlx0
• htsim -limit 1000 system_dlx0 RAMin RAMout
• htview system_dlx0
• Htmap system_dlx0

25
DLX0 instruction loop

• do -halted then
• ROMaddr!PC
• ROMdata?ir
• PCPC4
  auxPCPC4 PCPCaux
• case (ir cast Itype.0)
• is then LW()
• or then SW()
• or then if (ir cast
  Rtype.4 1) then SLT() fi
• or then BEQZ()
• or then J()
• or then haltedtrue
• si
• od