Tables 1 through 5 compare the SBus and PCI electrical, firmware, hardware, software, and normal transaction cycle features.
Table 1-1 Electrical Features Comparison
Feature |
SBus |
PCI |
Difference |
---|---|---|---|
Power consumption |
P=VI |
25W (5V x 5A) |
None |
Power supply |
5V +/-.25V 2A max per connector 12V +/-.75V 30mA max per connector |
5V +/-5% 5A max per connector 3.3V +/-.3V & .6A max per connector 12V +/-5% 500ma per connector -12V +/-10% 100ma per connector |
None
|
Table 1-2 Firmware Features Comparison
Feature |
SBus |
PCI |
Difference |
---|---|---|---|
FCode required |
All devices |
Boot and console devices |
None |
Table 1-3 Hardware Features Comparison
Feature |
SBus |
PCI |
Difference |
---|---|---|---|
Address allocation |
Static mapping. Slot has known start address and length |
Dynamic mapping for I/O and memory address spaces. Slot distinguished only by address of configuration space header. |
None |
Addressing mode |
Use virtual addressing. Require MMU in SBus controller and address translation. 32-bit virtual address for masters, 28-bit physical address space per slave. |
Normal address mode |
None |
Address spaces |
Standard chunk of memory-mapped space (28 bits/slot) |
Three physical address spaces: memory, I/O, configuration. |
None |
Auto-configuration |
|
|
|
Burst: Transfer mode size
|
Available. Up to 64 bytes: size declared in advance in SIZ{2:0}. |
Yes Variable size, no limit; determined by PCI device and PCI bridge. |
None |
Bus bandwidth: (data transfer rate) |
25MHz/32-bit, max. 100MBytes/sec for 32-bit. 200 MBytes/sec for 64-bit |
33MHz (rev 2.0) or 66 MHz for PCI/66, 32/64bit, maximum rate from 132MByte/second (33MHz/32-bit) to 528MByte/second (66 MHz/64-bit). |
None |
Bus parking |
No |
Yes. An arbiter may grant the busses to a master when the bus is idle and masters are not generating requests for the bus. If the master that the bus is parked on subsequently issues a request from the bus, it can immediately access it. |
None |
Bus width |
x 32-to 64-bit |
||
Clock frequency/bus speed |
Max CLK 25MHz CLK to out: 22nS Input Set-up: 15nS |
33MHz max CLK CLK to out:22ns Input Set-up: 7 ns |
Synchronous; signals referenced to rising clock edge |
Connectors |
One type of connector |
Either 5V or 3.3V 32-and 64-bit connectors; the 64-bit being an extension of the 32-bit |
None |
Data path |
32-bit, except 64-bit for extended transfers |
32/64-bit |
None |
Dynamic Bus Sizing |
Yes. Enables slave to control data width it accepts during non-burst transfers |
No, but same function is performed by Byte Enable setting during Data Phase |
None |
Form factors |
Single form factor per slot (double and triple-wide can share slots) |
Three form factors: short, long, and variable-height short |
None |
Interrupts |
Seven levels |
Four levels (INTA-D) |
None |
Max devices per bus |
Usually limited by electrical loading |
32 slots |
None |
Max functions per device |
1 |
8 |
None |
Max masters per bus |
8 |
32 |
None |
Pin count (connector) |
96 |
94 pins for both 32-bit and 64-bit connectors |
None |
Table 1-4 Software Features Comparison
Feature |
SBus |
PCI |
Difference |
---|---|---|---|
Parity |
Optional on data and virtual address transfers if parity generation and checking is implemented on controller and installed masters and slaves. |
Default during address and data phases; must be performed by all PCI-compliant devices. |
None |
Table 1-5 Normal Transaction Cycle
Address decode |
Slave selected by decode from controller |
Each target performs full 32-bit decoding and drives DEVSEL# if selected |
Burst size |
32 words |
No limit |
Bus driving and turnaround |
None |
A turnaround cycle is necessary for signals driven by more than one agent, to enable contention-avoidance when bus driving agents transfer a signal. |
Byte ordering and placement |
Byte-lane swapping |
DWORD swapping puts bytes in correct lane base on byte address |
Byte ordering |
Big-endian |
Little-endian |
Cycle participants |
Controller, Master, Slave |
PCI Agents: Master/Initiator, Target |
Cycle terminology and composition |
Transfer = 1. Arbitration Phase 2. Translation Phase 3. Extended Transfer Information Phase 4. Transfer Phase (also called Slave Cycle) |
Transfer = 1 or more clock cycles Phase = 1 or more read or write transfers, including (hidden) arbitration while current initiator is performing a data transfer
Read or write transaction = 1 address phase + 1 or more data phases |