Dynamic Scheduling

Report
CSCI/ EENG – 641 - W01
Computer Architecture 1
Prof. Babak Beheshti
Chapter 3 – Dynamic Scheduling
Slides based on the PowerPoint Presentations created by David Patterson as
part of the Instructor Resources for the textbook by Hennessy & Patterson
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
2
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
A Dynamic Algorithm: Tomasulo’s
• For IBM 360/91 (before caches!)
–  Long memory latency
• Goal: High Performance without special compilers
• Small number of floating point registers (4 in 360)
prevented interesting compiler scheduling of operations
– This led Tomasulo to try to figure out how to get more effective registers — renaming in
hardware!
• Why Study 1966 Computer?
• The descendants of this have flourished!
– Alpha 21264, Pentium 4, AMD Opteron, Power 5, …
3
Tomasulo Algorithm
• Control & buffers distributed with Function Units (FU)
– FU buffers called “reservation stations”; have pending operands
• Registers in instructions replaced by values or pointers to
reservation stations(RS); called register renaming ;
– Renaming avoids WAR, WAW hazards
– More reservation stations than registers, so can do optimizations compilers can’t
• Results to FU from RS, not through registers, over Common
Data Bus that broadcasts results to all FUs
– Avoids RAW hazards by executing an instruction only when its
operands are available
• Load and Stores treated as FUs with RSs as well
• Integer instructions can go past branches (predict taken),
allowing FP ops beyond basic block in FP queue
4
Tomasulo Organization
FP Registers
From Mem
FP Op
Queue
Load Buffers
Load1
Load2
Load3
Load4
Load5
Load6
Store
Buffers
Add1
Add2
Add3
Mult1
Mult2
FP adders
5
Reservation
Stations
To Mem
FP multipliers
Common Data Bus (CDB)
Reservation Station Components
Op: Operation to perform in the unit (e.g., + or –)
Vj, Vk: Value of Source operands
– Store buffers has V field, result to be stored
Qj, Qk: Reservation stations producing source registers
(value to be written)
– Note: Qj,Qk=0 => ready
– Store buffers only have Qi for RS producing result
Busy: Indicates reservation station or FU is busy
Register result status—Indicates which functional unit
will write each register, if one exists. Blank when no
pending instructions that will write that register.
6
Three Stages of Tomasulo Algorithm
1. Issue—get instruction from FP Op Queue
If reservation station free (no structural hazard),
control issues instr & sends operands (renames registers).
2. Execute—operate on operands (EX)
When both operands ready then execute;
if not ready, watch Common Data Bus for result
3. Write result—finish execution (WB)
Write on Common Data Bus to all awaiting units;
mark reservation station available
• Normal data bus: data + destination (“go to” bus)
• Common data bus: data + source (“come from” bus)
– 64 bits of data + 4 bits of Functional Unit source address
– Write if matches expected Functional Unit (produces result)
– Does the broadcast
• Example speed:
3 clocks for Fl .pt. +,-; 10 for * ; 40 clks for /
7
Instruction stream
Tomasulo Example
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
Load1
Load2
Load3
Register result status:
Clock
0
Clock cycle
counter
8
FU
No
No
No
3 Load/Buffers
Reservation Stations:
Time Name Busy
Add1
No
Add2
No
FU count
Add3
No
down
Mult1 No
Mult2 No
Busy Address
Op
S1
Vj
S2
Vk
RS
Qj
RS
Qk
3 FP Adder R.S.
2 FP Mult R.S.
F0
F2
F4
F6
F8
F10
F12
...
F30
Tomasulo Example Cycle 1
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
Reservation Stations:
Time Name Busy
Add1
No
Add2
No
Add3
No
Mult1 No
Mult2 No
Register result status:
Clock
1
9
FU
Busy Address
Load1
Load2
Load3
Op
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F0
F2
F4
F6
F8
Load1
Yes
No
No
34+R2
F10
F12
...
F30
Tomasulo Example Cycle 2
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
Reservation Stations:
Time Name Busy
Add1
No
Add2
No
Add3
No
Mult1 No
Mult2 No
Register result status:
Clock
2
FU
Busy Address
Load1
Load2
Load3
Op
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F0
F2
F4
F6
F8
Load2
Load1
Note: Can have multiple loads outstanding
10
Yes
Yes
No
34+R2
45+R3
F10
F12
...
F30
Tomasulo Example Cycle 3
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
Reservation Stations:
Time Name Busy Op
Add1
No
Add2
No
Add3
No
Mult1 Yes MULTD
Mult2 No
Register result status:
Clock
3
FU
F0
Busy Address
3
S1
Vj
Load1
Load2
Load3
S2
Vk
RS
Qj
Yes
Yes
No
34+R2
45+R3
F10
F12
RS
Qk
R(F4) Load2
F2
Mult1 Load2
F4
F6
F8
...
Load1
• Note: registers names are removed (“renamed”) in Reservation Stations;
MULT issued
• Load1 completing; what is waiting for Load1?
11
F30
Tomasulo Example Cycle 4
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
Reservation Stations:
Busy Address
3
4
4
Load1
Load2
Load3
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
No
Yes
No
45+R3
F10
F12
Time Name Busy Op
Add1 Yes SUBD M(A1)
Load2
Add2
No
Add3
No
Mult1 Yes MULTD
R(F4) Load2
Mult2 No
Register result status:
Clock
4
FU
F0
Mult1 Load2
M(A1) Add1
• Load2 completing; what is waiting for Load2?
12
...
F30
Tomasulo Example Cycle 5
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
2 Add1 Yes SUBD M(A1) M(A2)
Add2
No
Add3
No
10 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
5
FU
F0
Mult1 M(A2)
• Timer starts down for Add1, Mult1
13
No
No
No
F10
M(A1) Add1 Mult2
F12
...
F30
Tomasulo Example Cycle 6
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
1 Add1 Yes SUBD M(A1) M(A2)
Add2 Yes ADDD
M(A2) Add1
Add3
No
9 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
6
FU
F0
Mult1 M(A2)
Add2
No
No
No
F10
Add1 Mult2
• Issue ADDD here despite name dependency on F6?
14
F12
...
F30
Tomasulo Example Cycle 7
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
3
4
Busy Address
4
5
Load1
Load2
Load3
7
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
0 Add1 Yes SUBD M(A1) M(A2)
Add2 Yes ADDD
M(A2) Add1
Add3
No
8 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
7
FU
F0
No
No
No
Mult1 M(A2)
Add2
F10
Add1 Mult2
• Add1 (SUBD) completing; what is waiting for it?
15
F12
...
F30
Tomasulo Example Cycle 8
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
7
8
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
2 Add2 Yes ADDD (M-M) M(A2)
Add3
No
7 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
8
16
FU
F0
Mult1 M(A2)
No
No
No
F10
Add2 (M-M) Mult2
F12
...
F30
Tomasulo Example Cycle 9
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
7
8
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
1 Add2 Yes ADDD (M-M) M(A2)
Add3
No
6 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
9
17
FU
F0
Mult1 M(A2)
No
No
No
F10
Add2 (M-M) Mult2
F12
...
F30
Tomasulo Example Cycle 10
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
3
4
4
5
7
8
Busy Address
Load1
Load2
Load3
10
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
0 Add2 Yes ADDD (M-M) M(A2)
Add3
No
5 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
10
FU
F0
No
No
No
Mult1 M(A2)
F10
Add2 (M-M) Mult2
• Add2 (ADDD) completing; what is waiting for it?
18
F12
...
F30
Tomasulo Example Cycle 11
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
7
8
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
4 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
11
FU
F0
Mult1 M(A2)
F10
(M-M+M)(M-M) Mult2
• Write result of ADDD here?
• All quick instructions complete in this cycle!
19
No
No
No
F12
...
F30
Tomasulo Example Cycle 12
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
7
8
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
3 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
12
20
FU
F0
Mult1 M(A2)
No
No
No
F10
(M-M+M)(M-M) Mult2
F12
...
F30
Tomasulo Example Cycle 13
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
7
8
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
2 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
13
21
FU
F0
Mult1 M(A2)
No
No
No
F10
(M-M+M)(M-M) Mult2
F12
...
F30
Tomasulo Example Cycle 14
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
4
5
Load1
Load2
Load3
7
8
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
1 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
14
22
FU
F0
Mult1 M(A2)
No
No
No
F10
(M-M+M)(M-M) Mult2
F12
...
F30
Tomasulo Example Cycle 15
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
Busy Address
3
4
15
7
4
5
Load1
Load2
Load3
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
0 Mult1 Yes MULTD M(A2) R(F4)
Mult2 Yes DIVD
M(A1) Mult1
Register result status:
Clock
15
FU
F0
Mult1 M(A2)
No
No
No
F10
(M-M+M)(M-M) Mult2
• Mult1 (MULTD) completing; what is waiting for it?
23
F12
...
F30
Tomasulo Example Cycle 16
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
3
4
15
7
4
5
16
8
Load1
Load2
Load3
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
Mult1 No
40 Mult2 Yes DIVD M*F4 M(A1)
Register result status:
Clock
16
FU
F0
Busy Address
M*F4 M(A2)
F10
(M-M+M)(M-M) Mult2
• Just waiting for Mult2 (DIVD) to complete
24
No
No
No
F12
...
F30
Faster than light computation
(skip a couple of cycles)
25
Tomasulo Example Cycle 55
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
3
4
15
7
4
5
16
8
Load1
Load2
Load3
10
11
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
Mult1 No
1 Mult2 Yes DIVD M*F4 M(A1)
Register result status:
Clock
55
26
FU
F0
Busy Address
M*F4 M(A2)
No
No
No
F10
(M-M+M)(M-M) Mult2
F12
...
F30
Tomasulo Example Cycle 56
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
3
4
15
7
56
10
4
5
16
8
Load1
Load2
Load3
S1
Vj
S2
Vk
RS
Qj
RS
Qk
56
FU
F0
F2
F4
F6
F8
M*F4 M(A2)
No
No
No
11
Time Name Busy Op
Add1
No
Add2
No
Add3
No
Mult1 No
0 Mult2 Yes DIVD M*F4 M(A1)
Register result status:
Clock
Busy Address
F10
(M-M+M)(M-M) Mult2
• Mult2 (DIVD) is completing; what is waiting for it?
27
F12
...
F30
Tomasulo Example Cycle 57
Instruction status:
Instruction
LD
F6
LD
F2
MULTD F0
SUBD
F8
DIVD
F10
ADDD
F6
j
34+
45+
F2
F6
F0
F8
k
R2
R3
F4
F2
F6
F2
Exec Write
Issue Comp Result
1
2
3
4
5
6
Reservation Stations:
3
4
15
7
56
10
4
5
16
8
57
11
Load1
Load2
Load3
S1
Vj
S2
Vk
RS
Qj
RS
Qk
F2
F4
F6
F8
Time Name Busy Op
Add1
No
Add2
No
Add3
No
Mult1 No
Mult2 Yes DIVD M*F4 M(A1)
Register result status:
Clock
56
FU
F0
Busy Address
M*F4 M(A2)
No
No
No
F10
F12
...
(M-M+M)(M-M) Result
• Once again: In-order issue, out-of-order execution and out-oforder completion.
28
F30
Why can Tomasulo overlap iterations
of loops?
• Reservation stations: renaming to larger set of registers +
buffering source operands
– Prevents registers as bottleneck
– Avoids WAR hazards (by buffering old values of registers)
and avoids WAW hazards
– Allows loop unrolling in HW – “dynamic loop unrolling”
(Register Renaming: Multiple iterations use different
physical destinations for registers)
– Permits instruction issue to advance past integer control
flow operations
• Not limited to basic blocks
(integer units gets ahead, beyond branches)
• Other perspective: Tomasulo building data flow
dependency graph on the fly
29
Tomasulo’s scheme offers 2 major
advantages
1. Distribution of the hazard detection logic
– distributed reservation stations and the CDB
– If multiple instructions waiting on single result, & each
instruction has other operand, then instructions can be released
simultaneously by broadcast on CDB
– If a centralized register file were used, the units would have to
read their results from the registers when register buses are
available
2. Elimination of stalls for WAW and WAR hazards
30
Tomasulo Drawbacks
• Complexity
– delays of 360/91, MIPS 10000, Alpha 21264,
IBM PPC 620 in CA:AQA 2/e, but not in silicon!
• Many associative stores (CDB) at high speed
• Performance limited by Common Data Bus
– Each CDB must go to multiple functional units
high capacitance, high wiring density
– Number of functional units that can complete per cycle limited to one!
• Multiple CDBs  more FU logic for parallel assoc stores
• Non-precise interrupts!
– We will address this later
31
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
32
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
Speculation to greater ILP
• Greater ILP: Overcome control dependence
by hardware speculating on outcome of
branches and executing program as if
guesses were correct
– Speculation  fetch, issue, and execute instructions as if branch
predictions were always correct
– Dynamic scheduling  only fetches and issues instructions
• Essentially a data flow execution model:
Operations execute as soon as their
operands are available
33
Speculation to greater ILP
• 3 components of HW-based speculation:
1. Dynamic branch prediction to choose which
instructions to execute
2. Speculation to allow execution of
instructions before control dependences are
resolved
+ ability to undo effects of incorrectly speculated
sequence
3. Dynamic scheduling to deal with scheduling
of different combinations of basic blocks
34
Adding Speculation to Tomasulo
• Must separate execution from allowing
instruction to finish or “commit”
• This additional step called instruction
commit
• When an instruction is no longer speculative,
allow it to update the register file or memory
• Requires additional set of buffers to hold
results of instructions that have finished
execution but have not committed
• This reorder buffer (ROB) is also used to pass
results among instructions that may be
speculated
35
Reorder Buffer (ROB)
• In Tomasulo’s algorithm, once an instruction writes its
result, any subsequently issued instructions will find result
in the register file
• With speculation, the register file is not updated until the
instruction commits
– (we know definitively that the instruction should execute)
• Thus, the ROB supplies operands in interval between
completion of instruction execution and instruction commit
– ROB is a source of operands for instructions, just as reservation
stations (RS) provide operands in Tomasulo’s algorithm
– ROB extends architectured registers like RS
36
Reorder Buffer Entry
• Each entry in the ROB contains four fields:
1. Instruction type
• a branch (has no destination result), a store (has a memory address
destination), or a register operation (ALU operation or load, which has
register destinations)
2. Destination
• Register number (for loads and ALU operations) or
memory address (for stores)
where the instruction result should be written
3. Value
• Value of instruction result until the instruction commits
4. Ready
• Indicates that instruction has completed execution, and the value is
ready
37
Reorder Buffer operation
• Holds instructions in FIFO order, exactly as issued
• When instructions complete, results placed into ROB
– Supplies operands to other instruction between execution
complete & commit  more registers like RS
– Tag results with ROB buffer number instead of reservation
station
• Instructions commit values at head of ROB placed in
registers
Reorder
Buffer
• As a result, easy to undo
FP
Op
speculated instructions
Queue
FP Regs
on mispredicted branches
or on exceptionsCommit path
Res Stations
FP Adder
38
Res Stations
FP Adder
Recall:
4 Steps of Speculative Tomasulo
Algorithm
1. Issue—get instruction
from FP Op Queue
If reservation station and reorder buffer slot free, issue
instr & send operands & reorder buffer no. for
destination (this stage sometimes called “dispatch”)
2. Execution—operate on operands (EX)
When both operands ready then execute; if not ready,
watch CDB for result; when both in reservation station,
execute; checks RAW (sometimes called “issue”)
3. Write result—finish execution (WB)
Write on Common Data Bus to all awaiting FUs
& reorder buffer; mark reservation station available.
4. Commit—update register with reorder result
When instr. at head of reorder buffer & result present,
update register with result (or store to memory) and
remove instr from reorder buffer. Mispredicted branch
flushes reorder buffer (sometimes called “graduation”)
39
Tomasulo With Reorder buffer:
Done?
FP Op
Queue
ROB7
ROB6
Newest
ROB5
Reorder Buffer
ROB4
ROB3
ROB2
F0
LD F0,10(R2)
Registers
Dest
40
ROB1
To
Memory
from
Memory
Dest
FP adders
N
Reservation
Stations
Dest
1 10+R2
FP multipliers
Oldest
Tomasulo With Reorder buffer:
Done?
FP Op
Queue
ROB7
ROB6
Newest
ROB5
Reorder Buffer
ROB4
ROB3
F10
F0
ADDD F10,F4,F0
LD F0,10(R2)
Registers
Dest
2 ADDD R(F4),ROB1
FP adders
41
N
N
ROB2
ROB1
To
Memory
from
Memory
Dest
Reservation
Stations
Dest
1 10+R2
FP multipliers
Oldest
Tomasulo With Reorder buffer:
Done?
FP Op
Queue
ROB7
ROB6
Newest
ROB5
Reorder Buffer
ROB4
F2
F10
F0
DIVD F2,F10,F6
ADDD F10,F4,F0
LD F0,10(R2)
Registers
Dest
2 ADDD R(F4),ROB1
FP adders
42
N
N
N
ROB3
ROB2
ROB1
To
Memory
Dest
3 DIVD ROB2,R(F6)
Reservation
Stations
from
Memory
Dest
1 10+R2
FP multipliers
Oldest
Tomasulo With Reorder buffer:
Done?
FP Op
Queue
ROB7
Reorder Buffer
F0
F4
-F2
F10
F0
ADDD F0,F4,F6
LD F4,0(R3)
BNE F2,<…>
DIVD F2,F10,F6
ADDD F10,F4,F0
LD F0,10(R2)
Registers
Dest
2 ADDD R(F4),ROB1
6 ADDD ROB5, R(F6)
FP adders
43
N
N
N
N
N
N
ROB6
ROB5
ROB4
ROB3
ROB2
ROB1
To
Memory
Dest
3 DIVD ROB2,R(F6)
Reservation
Stations
FP multipliers
from
Memory
Dest
1 10+R2
5 0+R3
Newest
Oldest
Tomasulo With Reorder buffer:
FP Op
Queue
Reorder Buffer
-- ROB5
F0
F4
-F2
F10
F0
Done?
ST 0(R3),F4
N ROB7
ADDD F0,F4,F6
N ROB6
LD F4,0(R3)
N ROB5
BNE F2,<…>
N ROB4
DIVD F2,F10,F6 N ROB3
ADDD F10,F4,F0 N ROB2
LD F0,10(R2)
N ROB1
Registers
Dest
2 ADDD R(F4),ROB1
6 ADDD ROB5, R(F6)
FP adders
44
To
Memory
Dest
3 DIVD ROB2,R(F6)
Reservation
Stations
FP multipliers
from
Memory
Dest
1 10+R2
5 0+R3
Newest
Oldest
Tomasulo With Reorder buffer:
FP Op
Queue
Reorder Buffer
-- M[10]
F0
F4 M[10]
-F2
F10
F0
Done?
ST 0(R3),F4
Y ROB7
ADDD F0,F4,F6
N ROB6
LD F4,0(R3)
Y ROB5
BNE F2,<…>
N ROB4
DIVD F2,F10,F6 N ROB3
ADDD F10,F4,F0 N ROB2
LD F0,10(R2)
N ROB1
Registers
Dest
2 ADDD R(F4),ROB1
6 ADDD M[10],R(F6)
FP adders
45
To
Memory
Dest
3 DIVD ROB2,R(F6)
Reservation
Stations
from
Memory
Dest
1 10+R2
FP multipliers
Newest
Oldest
Tomasulo With Reorder buffer:
FP Op
Queue
Reorder Buffer
Done?
-- M[10] ST 0(R3),F4
Y ROB7
F0 <val2> ADDD F0,F4,F6 Ex ROB6
F4 M[10] LD F4,0(R3)
Y ROB5
-BNE F2,<…>
N ROB4
F2
DIVD F2,F10,F6 N ROB3
F10
ADDD F10,F4,F0 N ROB2
F0
LD F0,10(R2)
N ROB1
Registers
Dest
2 ADDD R(F4),ROB1
FP adders
46
To
Memory
Dest
3 DIVD ROB2,R(F6)
Reservation
Stations
from
Memory
Dest
1 10+R2
FP multipliers
Newest
Oldest
Tomasulo With Reorder buffer:
FP Op
Queue
Reorder Buffer
What about memory
hazards???
Done?
-- M[10] ST 0(R3),F4
Y ROB7
F0 <val2> ADDD F0,F4,F6 Ex ROB6
F4 M[10] LD F4,0(R3)
Y ROB5
-BNE F2,<…>
N ROB4
F2
DIVD F2,F10,F6 N ROB3
F10
ADDD F10,F4,F0 N ROB2
F0
LD F0,10(R2)
N ROB1
Registers
Dest
2 ADDD R(F4),ROB1
FP adders
47
To
Memory
Dest
3 DIVD ROB2,R(F6)
Reservation
Stations
from
Memory
Dest
1 10+R2
FP multipliers
Newest
Oldest
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
48
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
Avoiding Memory Hazards
• WAW and WAR hazards through memory are eliminated
with speculation because actual updating of memory
occurs in order, when a store is at head of the ROB, and
hence, no earlier loads or stores can still be pending
• RAW hazards through memory are maintained by two
restrictions:
1. not allowing a load to initiate the second step of its execution if
any active ROB entry occupied by a store has a Destination field
that matches the value of the A field of the load, and
2. maintaining the program order for the computation of an
effective address of a load with respect to all earlier stores.
• these restrictions ensure that any load that accesses a
memory location written to by an earlier store cannot
perform the memory access until the store has written the
data
49
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
50
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
Exceptions and Interrupts
• IBM 360/91 invented “imprecise interrupts”
– Computer stopped at this PC; its likely close to this address
– Not so popular with programmers
– Also, what about Virtual Memory? (Not in IBM 360)
• Technique for both precise interrupts/exceptions and
speculation: in-order completion and in-order commit
– If we speculate and are wrong, need to back up and restart
execution to point at which we predicted incorrectly
– This is exactly same as need to do with precise exceptions
• Exceptions are handled by not recognizing the
exception until instruction that caused it is ready to
commit in ROB
– If a speculated instruction raises an exception, the
exception is recorded in the ROB
– This is why reorder buffers in all new processors
51
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
52
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
Increasing Instruction Fetch Bandwidth
Branch Target Buffer (BTB)
Predicts next
instruct address,
sends it out
before decoding
instructuction
PC of branch sent
to BTB
When match is
found, Predicted
PC is returned
If branch
predicted taken,
instruction fetch
continues at
Predicted PC
•
•
•
•
53
IF BW: Return Address Predictor
70%
Misprediction frequency
• Small buffer of
return addresses
acts as a stack
• Caches most
recent return
addresses
• Call  Push a
return address
on stack
• Return  Pop an
address off stack &
predict as new PC
go
m88ksim
60%
cc1
50%
compress
40%
xlisp
ijpeg
30%
perl
20%
vortex
10%
0%
0
1
2
4
8
16
Return address buffer entries
54
More Instruction Fetch Bandwidth
• Integrated branch prediction branch predictor is
part of instruction fetch unit and is constantly
predicting branches
• Instruction prefetch Instruction fetch units
prefetch to deliver multiple instruct. per clock,
integrating it with branch prediction
• Instruction memory access and buffering
Fetching multiple instructions per cycle:
– May require accessing multiple cache blocks (prefetch to hide
cost of crossing cache blocks)
– Provides buffering, acting as on-demand unit to provide
instructions to issue stage as needed and in quantity needed
55
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
56
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
Speculation: Register Renaming vs.
ROB
• Alternative to ROB is a larger physical set of registers
combined with register renaming
– Extended registers replace function of both ROB and reservation
stations
• Instruction issue maps names of architectural
registers to physical register numbers in extended
register set
– On issue, allocates a new unused register for the destination
(which avoids WAW and WAR hazards)
– Speculation recovery easy because a physical register holding an
instruction destination does not become the architectural register until
the instruction commits
• Most Out-of-Order processors today use extended
registers with renaming
57
Outline
• Dynamic Scheduling
– Tomasulo Algorithm
• Speculation
– Speculative Tomasulo Example
•
•
•
•
•
58
Memory Aliases
Exceptions
Increasing instruction bandwidth
Register Renaming vs. Reorder Buffer
Value Prediction
Value Prediction
• Attempts to predict value produced by instruction
– E.g., Loads a value that changes infrequently
• Value prediction is useful only if it significantly
increases ILP
– Focus of research has been on loads; so-so results, no processor
uses value prediction
• Related topic is address aliasing prediction
– RAW for load and store or WAW for 2 stores
• Address alias prediction is both more stable and
simpler since need not actually predict the address
values, only whether such values conflict
– Has been used by a few processors
59
(Mis) Speculation on Pentium 4
Misspeculation Fraction
• % of micro-ops not used
45%
43% 45%
39%
40%
35%
30%
24% 24%
25%
20%
20%
15%
10%
3%
1%1%0%
5%
0%
173.applu
171.swim
Integer
crafty
gcc
gzip
60
Floating Point
Perspective
• Interest in multiple-issue because wanted to improve
performance without affecting uniprocessor
programming model
• Taking advantage of ILP is conceptually simple, but
design problems are amazingly complex in practice
• Conservative in ideas, just faster clock and bigger
• Processors of last 5 years (Pentium 4, IBM Power 5,
AMD Opteron) have the same basic structure and
similar sustained issue rates (3 to 4 instructions per
clock) as the 1st dynamically scheduled, multiple-issue
processors announced in 1995
– Clocks 10 to 20X faster, caches 4 to 8X bigger, 2 to 4X as
many renaming registers, and 2X as many load-store units
 performance 8 to 16X
• Peak v. delivered performance gap increasing
61
Summary … #2
• Reservations stations: renaming to larger set of registers + buffering source operands
– Prevents registers as bottleneck
– Avoids WAR, WAW hazards
– Allows loop unrolling in HW
• Not limited to basic blocks: integer units get ahead, beyond branches
• Dynamic Scheduling
• Interrupts and Exceptions either interrupt the current instruction or happen between
instructions
– Possibly large quantities of state must be saved before
interrupting
• Machines with precise exceptions provide one single point in the program to restart
execution
– All instructions before that point have completed
– No instructions after or including that point have completed
• Hardware techniques exist for precise exceptions even in the face of
out-of-order execution!
– Important enabling factor for out-of-order execution
62
Appendix
Simplified Tomasulo Algorithm
Example
• Simulate the execution of the below using
Tomasulo's algorithm. Assume dual dispatch and
a dual common data bus, neither dispatch nor
broadcast being counted as separate cycle.
Add/subtract takes 2 cycles and Multiply/divide
takes 3 cycles. Make more charts as needed.
• i: R4 <- R0 + R2
• j: R8 <- R0 * R4
• k: R4 <- R4 - R2
Notes
• Put a 0 in tag for any operand that is known and does
not need to be calculated by another FU
• Put a number in the tag field for an operand
corresponding to the number to the left of the RS
location calculating that operand
• Do not put any intermediate data in the Data field, as
they will be bypassed directly to the tag they were
depend on. Just the final answers will be put in data
fields.
• When a register’s value does not depend on a different
tag – change its tag value in the rightmost table
Planning…
Cycle ->
instruction
i R0+R2->R4
j R0*R4->R8
k R4-R2->R4
0
1
D+E
D
E
D
2
3
4
E
E
E
E
E
5
B
D: Dispatch (No additional cycle)
E: Execute
B: Broadcast(No additional cycle)
B
B
6
Cycle 0
Cycle 0: Dispatch i, j
Tag Sink Tag Source
1 0
2.0
0
2
3.5
Tag Sink Tag Source
4 0
2.0
1
5
3
Multiplier
Adder
----
Busy Tag Data
0
2.0
2
3.5
4 Yes
1
10.0
8 Yes
4
7.8
Cycle 1
Cycle 1: Dispatch k; Executed i
Tag Sink Tag Sourc
e
1 0
2.0 0
3.5
Tag Sink Tag Sourc
e
4 0
2.0 1
----
0
2.0
2 1
5
2
3.5
3
----
0
i
Adder
3.5
Multiplier
Busy Tag Data
4 Yes
2
----
8 Yes
4
----
Cycle 2
Cycle 2: Executing j, k
Tag Sink Tag Sourc
e
1
2 0
5.5
0
3
3.5
Tag Sink Tag Sourc
e
4 0
2.0 0
5.5
0
5
2
Multiplier
Adder
Bus Tag Data
y
2.0
3.5
4 Yes
2
----
8 Yes
4
----
Cycle 3
Cycle 3: Executed k
Tag Sink Tag Source
1
2 0
3
5.5
0
k
Adder
3.5
Tag Sink Tag Source
4 0
2.0 0
5.5
5
Multiplier
Busy Tag Data
0
2.0
2
3.5
4 Yes
2
---8 Yes
4
----
Cycle 4
Cycle 4: Executed j
Tag Sink Tag Source
Tag Sink Tag Source
1
4 0
2
5
3
2.0
0
j
Multiplier
Adder
5.5
Busy Tag Data
0
2.0
2
3.5
4
2.0
8 Yes
4
Cycle 5: R8 = 11
Total number of cycle to complete the code: 5 to complete or 6 to update FLR
----
• Simulate the execution of the code using
Tomasulo's algorithm. Assume single dispatch
and a single common data bus, dispatch not
being counted as separate cycle but broadcast
taking 1 cycle. Add/subtract takes 2 cycles,
and Multiply takes 3 cycles. Make more charts
as needed.
Planning…
Cycle ->
instruction
i R0+R2->R4
j R0*R4->R8
k R4-R2->R4
0
1
2
D+E E
D
B
D
3
4
5
6
E
E
E
E
E
B
B
D: Dispatch (No additional cycle)
E: Execute
B: Broadcast(No additional cycle)
7
8
Cycle 0

similar documents