NAME

cpu —

HP PA-RISC CPU

SYNOPSIS

cpu* at mainbus0 irq 31

DESCRIPTION
FLOATING-POINT COPROCESSOR
SUPERSCALAR EXECUTION
PERFORMANCE MONITOR COPROCESSOR
DEBUG SPECIAL UNIT
SEE ALSO
HISTORY

DESCRIPTION

The following table lists the PA-RISC CPU types and their characteristics, such as TLB, maximum cache sizes (where the ‘*’ character means on-chip) and HP 9000/700 machines they were used in (see also intro(4) for the reverse list).

CPU	PA	Clock	Caches	TLB	BAT	Models
		MHz max	KB max
7000	1.1a	66	256 L1I	96I	4I	705, 710, 720
			256 L1D	96D	4D	730, 750
7100	1.1b	100	1024 L1I	120	16	715/33/50/75
			2048 L1D			725/50/75
						{735,755}/100
						742i, 745i, 747i
7150	1.1b	125	1024 L1I	120	16	735/125, 755/125
			2048 L1D
7100LC	1.1c	100	1 L1I*	64	8	712/60/80/100
			1024 L2I			715/64/80/100
			1024 L2D			715/100XC
						725/64/100
						743i, 748i
						SAIC
7200	1.1d	140	2 L1*	120	16	C100, C110
			1024 L2I			J200, J210
			1024 L2D
7300LC	1.1e	180	64 L1I*	96	8	A180, A180C
			64 L1D*			B132, B160, B180
			8192 L2			C132L, C160L
						744, 745, 748
						RDI PrecisionBook
8000	2.0	180	1024 L1I	96		C160, C180
			1024 L1D			J280, J282
8200	2.0	300	2048 L1I	120		C200, C240
			2048 L1D			J2240
8500	2.0	440	512 L1I*	160		A400, A500, C360
			1024 L1D*			B1000, B2000, C3000
						J5000, J7000
8600	2.0	550	512 L1I*	160		A400, A500, C3600
			1024 L1D*			B2000, B2600
						J5600, J6000, J7600
8700	2.0	875	768 L1I*	240		A400, A500, J6700
			1536 L1D*			C3650, C3700, C3750

FLOATING-POINT COPROCESSOR

The following table summarizes available floating-point coprocessor models for the 32-bit PA-RISC processors.

FPU	Model
Indigo
Sterling I MIU (TYCO)
Sterling I MIU (ROC w/Weitek)
FPC (w/Weitek)
FPC (w/Bit)
Timex-II
Rolex	725/50, 745i
HARP-I
Tornado	J2x0,C1x0
PA-50 (Hitachi)
PCXL	712/60/80/100

SUPERSCALAR EXECUTION

The following table summarizes the superscalar execution capabilities of 32-bit PA-RISC processors.

CPU	Units	Bundles
7100	1 integer ALU	load-store/fp
	1 FP	int/fp
		branch/*
7100LC	2 integer ALU	load-store/int
	1 FP	load-store/fp
		int/fp
		branch/*
7200	2 integer ALU	load-store/int
	1 FP	load-store/fp
		int/int
		int/fp
		branch/*
7300LC	2 integer ALU	load-store/int
	1 FP	load-store/fp
		int/fp
		branch/*
8x00	2 integer ALU	4-way superscalar
	2 shift/merge
	2 load/store
	2 FPU mul/add
	2 FPU div/sqrt

In conclusion, all of the above CPUs are dual-issue, or 2-way superscalar, with the exception that on CPUs with two integer ALUs only one of these units is capable of doing shift, load/store and test operations. Additionally, there are several kinds of restrictions placed upon the superscalar execution:

For the purpose of showing which instructions are allowed to proceed together through the pipeline, they are divided into classes:

Class	Description
flop	floating point operation
ldst	loads and stores
flex	integer ALU
mm	shifts, extracts and deposits
nul	might nullify successor
bv	BV, BE
br	other branches
fsys	FTEST and FP status/exception
sys	system control instructions

For CPUs with two integer ALUs (7100LC, 7200, 7300LC), the following table lists the instructions which are allowed to be executed concurrently:

First	Second instruction
flop	+ ldst/flex/mm/nul/bv/br
ldst	+ flop/flex/mm/nul/br
flex	+ flop/ldst/flex/mm/nul/br/fsys
mm	+ flop/ldst/flex/fsys
nul	+ flop
sys	never bundled

ldst + ldst is also possible under certain circumstances, which is then called "double word load/store".

The following restrictions are placed upon the superscalar execution:

An instruction that modifies a register will not be bundled with another instruction that takes this register as operand. Exception: a flop can be bundled with an FP store of the flop's result register.
An FP load to one word of a doubleword register will not be bundled with a flop that uses the other doubleword of this register.
A flop will not be bundled with an FP load if both instructions have the same target register.
An instruction that could set the carry/borrow bits will not be bundled with an instruction that uses carry/borrow bits.
An instruction which is in the delay slot of a branch is never bundled with other instructions.
An instruction which is at an odd word address and executed as a target of a taken branch is never bundled.
An instruction which might nullify its successor is never bundled with this successor. Only if the successor is a flop instruction is this bundle allowed.

PERFORMANCE MONITOR COPROCESSOR

The performance monitor coprocessor is an optional, implementation-dependent coprocessor which provides a minimal common software interface to implementation-dependent performance monitor hardware.

DEBUG SPECIAL UNIT

The debug special function unit is an optional, architected SFU which provides hardware assistance for software debugging using breakpoints. The debug SFU is currently defined only for Level 0 processors.

HISTORY

The cpu driver was written by Michael Shalayeff <mickey@openbsd.org> for the HPPA port for OpenBSD 2.5.

TABLE OF CONTENTS