Intel Pentium M 765, Pentium M 735, Pentium M 755, Pentium M 745, Pentium M 725, Pentium M 715, Pentium M 778, Pentium M 758, Pentium M 738, Pentium M 773, Pentium M 753, Pentium M 733J, Pentium M 733, Pentium M 723 Datasheet
Intel® Pentium® M Processor on
90 nm Process with 2-MB L2
Cache
Datasheet
January 2006
Document Number: 302189-008
IINFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL® PRODUCTS. NO LICENSE, EXPRESS OR IMPLIED, BY
ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PRO PERTY RIGHTS IS GRANTED BY THIS DOCUMENT. EXCEPT AS PROVIDED IN
INTEL'S TERMS AND CONDITIONS OF SALE FOR SUCH PRODUCTS, INTEL ASSUMES NO LIABILITY WHA TSOEVER, AND INTEL DISCLAIMS
ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO SALE AND/OR USE OF INTEL PRODUCTS INCLUDING LIABILITY OR WARRANTIES
RELATING T O FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANY P ATENT, COPYRIGHT OR OTHER
INTELLECTUAL PROPERTY RIGHT. Intel products are not intended for use in medical, life saving, life sustaining applications.
Intel may make changes to specifications and product descriptions at any time, without notice.
Designers must not rely on the absence or characteristics of any features or instructions marked “reserved” or “un defined.” Intel reserves these for
future definition and shall have no responsibility whatsoever for conflicts or incompatibilities arising from future changes to them.
®
The Intel
product to deviate from published specifications. Current characterized errata are available on request.
Contact your local Intel sales office or your distributor to obtain the latest specifications and before placing your product order.
.
different processor families. See www.intel.com/products/processor_number for details.
Intel, Pentium, Celeron, MMX, Intel SpeedStep and the In tel logo are tr ademarks or re gistered tra demarks of Intel Cor poration or it s subsidiaries in the
3-3 Processor DC Absolute Maximum Ratings....... ... ... .... ... ... ... .... ... ... ....................................... ... ...21
3-4 Voltage and Current Specifications - Standard Voltage Processors ..........................................22
3-5 Voltage and Current Specifications - Low Voltage Processors ..................................................24
3-6 Voltage and Current Specifications - Ultra Low Voltage Processors..........................................26
3-7 Voltage and Current Specifications (Continued).........................................................................28
3-8 Voltage Tolerances for the Intel
3-9 Voltage Tolerances for the Intel
3-10Voltage Tolerances for the Intel
3-11Voltage Tolerances for the Intel
3-12Voltage Tolerances for the Intel
3-13Voltage Tolerances for the Intel
3-14Voltage Tolerances for the Intel
3-15Voltage Tolerances for the Intel
3-16Voltage Tolerances for the Intel
3-17Voltage Tolerances for the Intel
3-18Voltage Tolerances for the Intel
3-19Voltage Tolerances for the Intel
3-20Voltage Tolerances for the Intel
3-21Voltage Tolerances for the Intel
Pentium® M Processor (Active State) VID#A........................31
®
Pentium® M Processor (Deep Sleep State) VID#A ...............32
®
Pentium® M Processor (Active State) VID#B........................33
®
Pentium® M Processor (Deep Sleep State) VID#B ...............34
®
Pentium® M Processor (Active State) VID#C........................35
®
Pentium® M Processor (Deep Sleep State) VID#C...............36
®
Pentium® M Processor (Active State) VID#D........................37
®
Pentium® M Processor (Deep Sleep State) VID#D...............38
®
Pentium® M Processor (Active State) VID#E........................39
®
Pentium® M Processor (Deep Sleep State) VID#E ...............40
®
Pentium® M Processor LV (Active State)..............................41
®
Pentium® M Processor LV (Deep Sleep State).....................42
®
Pentium® M Processor ULV (Active State)............................42
®
Pentium® M Processor ULV (Deep Sleep State)...................43
®
Pentium M Processor..........................................................78
Datasheet 5
Revision History
RevisionDescriptionDate
001Initial release of datasheetMay 2004
002Added Intel
• Specifications of Intel
003
004Added Intel
005
006• Added Intel
007
008Added Intel
• Chapter 2 section 2.1.3 - Missing Stop Grant State title added.
• Table 4 - Max ratings specifications updated
• Added Intel
• Added Execute Disable support feature and lead free SLI
• Added Table 3-20 AGTL + Signal Group Signal DC
• Table 3-18 - Voltage Tolerances for Intel
Updated Intel
for optimized VID
®
Pentium® M processor 725 and 715 specificationsJune 2004
and Ultra Low Voltage 733 & 723 added in chapter 3 and chapter
5.
Description was previously merged with Auto Halt state section
and is unchanged.
®
Pentium® M processor 765 specificationsOctober 2004
®
Pentium® M processor 753 and 758 specifications
(second layer interconnect) Micro-FCPGA packaging
information in chapter 1
Specifications
processor ULV (Deep Sleep State) updated
®
Pentium® M processor 778 specificationsJuly 2005
®
Pentium® M processor 753 and 733J specifications
®
Pentium® M processor 773 specificationsJanuary 2006
®
Pentium® M processor Low Voltage 738
®
Pentium® M
July 2004
January 2005
July 2005
§
6Datasheet
1Introduction
The Intel® Pentium® M processor based on 90 nm process technology featuring 2-MB L2 cache
and 400-MHz front side bus (FSB) is the next generation high- performance, low-power mobile
processor based on the Intel
®
Pentium® processor architecture.
Introduction
Throughout this document, Intel Pentium M processor based on 90 nm technology featuring 2-MB
L2 cache and 400 MHz FSB will be referred to as Pentium
including low voltage and ultra low voltage processors.
This document contains specifications for the Pentium M processors 765/ 755/ 745/ 735/ 725/ 715
Standard Voltage, 778/758/738 Low Voltage and 773/753/733J/733/723 Ultra Low Voltage
Intel processor numbers are not a measure of performance. Processor numbers differentiate
features within each processor family, not across different processor families. See www.intel.com/
products/processor_number for details.
The following list provides some of the key features on this processor:
• Supports Intel
®
Architecture with Dynamic Execution
M processor, or simply the processor,
.
• On-die, primary 32-KB instruction cache and 32-KB write-back data cache
• On-die, 2 MB second level cache with Advanced Transfer Cache Architecture
• Way set associativity and ECC (Error Correcting Code) support
• Data Prefetch Logic
• Streaming SIMD extensions 2 (SSE2)
• 400 MHz, source-synchronous FSB
• Advanced power management features including Enhanced Intel SpeedStep
®
technology
• Micro-FCPGA and Micro-FCBGA packaging technologies
• Manufactured on Intel’s advanced 90 nanometer process technology with copper interconnect.
• Support for MMX™ technology and Internet Streaming SIMD instructions
• The processor’s data prefetch logic fetches data to the L2 cache before L1 cache requests
occurs, resulting in reduced bus cycle penalties and improved performance
• Micro-FCPGA and Micro-FCBGA packaging technologies, includ ing lead free SLI (second
level interconnect) technology for the Micro-FCBGA package (for Pentium M processors 755,
745, 778, 758, 738, 773, 753, 733J/733, 723)
• Execute Disable Bit support for enhanced security (available on processors with CPU
Signature = 06D8h and recommended for implementation on Intel
family-based platforms only)
The Pentium M processor will be manufactured on Intel’s advanced 90 nm process technology
with copper interconnect. The processor maintains support for MMX technology and Internet
Streaming SIMD instructions and full compatibility with IA-32 software. The on-die, 32-KB
Level 1 instruction and data caches along with the 2-MB L2 cache with advanced transfer cache
Datasheet 7
®
915 Express chipset
Introduction
architecture enable significant performance improvement over existing mobile processors. The
processor’s data prefetch logic fetches data to the L2 cache before L1 cache requests occurs,
resulting in reduced bus cycle penalties and improved performance.
The streaming SIMD extensions 2 (SSE2) enable break-through levels of performance in
multimedia applications including 3-D graphics, video decoding/encoding, and speech recognition.
The new packed double-precision floating-point instructions enhance performance for applications
that require greater range and precision, including scientific and engineering applications and
advanced 3-D geometry techniques, such as ray tracing.
The Pentium M processor’s 400-MHz FSB utilizes a split-transaction, deferred reply protocol. The
400-MHz FSB uses source-synchronous transfer (SST) of address and data to improve
performance by transferring data four times per bus clock (4X data transfer rate, as in AGP 4X).
Along with the 4X data bus, the address bus can deliver addresses two times per bus clock and is
referred to as a “double-clocked” or 2X address bus. Working together, the 4X data bus and 2X
address bus provide a data bus bandwidth of up to 3.2 GB/second. The FSB uses Advanced
Gunning Transceiver Logic (AGTL+) signaling technolo gy, a variant of GTL+ signaling
technology with low power enhancements.
The processor features Enhanced Intel SpeedStep technology, which enables real-time dynamic
switching between multiple voltage and frequen cy points. This results in optimal performance
without compromising low power. The processor features the Auto Halt, Stop Grant, Deep Sleep,
and Deeper Sleep low power states.
The Pentium M processor utilizes socketable Micro Flip-Chip Pin Grid Array (Micro-FCPGA) and
surface mount Micro Flip-Chip Ball Grid Array (Micro-FCBGA) package technology. The MicroFCPGA package plugs into a 479-hole, surface-mount, zero insertion force (ZIF) socket, which is
referred to as the mPGA479M socket.
Pentium M processors with CPU Signature = 06D8h will also include the Execute Disable Bit
capability . This feature combined with a support operating system allows memory to be marked as
executable or non executable. If code attempts to run in non-executable memory the processor
raises an error to the operating system. This feature can prevent some classes of viruses or worms
that exploit buffer overrun vulnerabilities and can thus help improve the overall security of the
system. See the Intel
®
Architecture Software Developer's Manual for more detailed information.
Intel will validate this feature only on Intel 915 Express chipset family based platforms and
recommends customers implement BIOS changes related to this feature, only on Intel 915 Express
chipset family based platforms.
Note: The term AGTL+ is used to refer to Assisted GTL+ signalling technology on some Intel processors.
8Datasheet
1.1Terminology
TermDefinition
#A “#” symbol after a signal name refers to an active low signal, indicating a signal is in
Front Side Bus
(FSB)
the active state when driven to a low level. For example, when RESET# is low, a reset
has been requested. Conversely, when NMI is high, a nonmaskable interrupt has
occurred. In the case of signals where the name does not imply an active state but
describes part of a binary sequence (such as address or data), the “#” symbol implies
that the signal is inverted. For example, D[3:0] = “HLHL” refers to a hex ‘A’, and
D[3:0]# = “LHLH” also refers to a hex “A” (H= High logic level, L= Low logic level).
XXXX means that the specification or value is yet to be determined.
Refers to the interface between the processor and system core logic (also known as
the chipset components).
1.2References
Material and concepts available in the following documents may be beneficial when reading this
document. Please note that “platform design guides,” when used throughout this document, refers
to the platform design guides listed below:
Introduction
Table 1-1. References (Sheet 1 of 2)
Intel Pentium M Processor on 90 nm Process with 2-MB L2 Cache Specification Update
Mobile Intel
Mobile Intel
Update
Intel
Intel
Intel
Intel
Intel
Datasheet
Intel
Chipset Specification Update
Intel
915PM/GM/GMS and 910GML Express Chipset Datasheethttp://www.intel.com/
915PM/GM/GMS and 910GML Express Chipset Specification
855PM Chipset Platform Design Guide: For use with IntelPentium M and
Volume 1: Basic Architecture
Volume 2A: Instruction Set Reference
Volume 2B: Instruction Set Reference
Volume 3: System Programming Guide
NOTE: Contact your Intel representative for the latest revision and document number of this document.
Document Number/
Location
design/pentium4/
manuals/index_new.htm
§
1
10Datasheet
2Low Power Features
2.1Clock Control and Low Power States
The Pentium M processor supports the AutoHALT Power-Down, Stop Grant, Sleep, Deep Sleep,
and Deeper Sleep states for optimal power management. See Figure 2-1 for a visual representation
of the processor low-power states.
Figure 2-1. Clock Control States
Low Power Features
STPCLK# asserted
NormalSleep
halt
break
instruction
Auto Halt
STPCLK# deasserted
HLT
Halt break - A20M#, INIT#, INTR, N MI, PREQ#, RESET# , S MI#, or APIC interrupt
2.1.1Normal State
This is the normal operating state for the processor.
STPCLK#
asserted
STPCLK#
deasserted
snoop
occurs
snoop
serviced
Stop
Grant
snoop
serviced
HALT/
Grant
Snoop
snoop
occurs
SLP# asserted
SLP# deasserted
core voltage raised
Deeper
Sleep
core voltage lowered
V0001-04
DPSLP#
de-asserted
DPSLP#
asserted
Deep
Sleep
2.1.2AutoHALT Power-Down State
AutoHALT Power-Down is a low-power state entered when the processor executes the HALT
instruction. The processor will transition to the Normal state upon the occurrence of SMI#, INIT#,
LINT[1:0] (NMI, INTR), or FSB interrupt me ss age. RESET# will cause the processor to
immediately initialize itself.
A system management interrupt (SMI) handler will return execution to either Normal state or the
AutoHALT Power-Down state. See the IA-32 IntelVolume 3: System Programmer's Guide for more information.
Datasheet 11
®
Architecture Software Developer's Manual,
Low Power Features
The system can generate a STPCLK# while the processor is in the AutoHALT Power-Down state.
When the system deasserts the STPCLK# interrupt, the processor will return execution to the
HALT state.
While in AutoHALT Power-Down state, the processor will process bus snoops and interrupts.
2.1.3Stop-Grant State
When the STPCLK# pin is asserted, the Stop-Grant state of the processor is entered 20 bus clocks
after the response phase of the processor-issued Stop Grant Acknowledge special bus cycle.
Since the AGTL+ signal pins receive power from the FSB, these pins should not be driven
(allowing the level to return to V
state. In addition, all other input pins on the FSB should be driven to the inactive state.
RESET# will cause the processor to immediately initialize itself, but the processor will stay in
Stop-Grant state. A transition back to the Normal state will occur with the de-assertion of the
STPCLK# signal. When re-entering the Stop-Grant state from the Sleep state, STPCLK# should be
deasserted ten or more bus clocks after the de-assertion of SLP#.
A transition to the HALT/Grant Snoop state will occur when the processor detects a snoop on the
FSB (see Section 2.1.3). A transition to the Sleep state (see Section 2.1.5) will occur with the
assertion of the SLP# signal.
) for minimum power drawn by the termination resistors in this
CCP
While in the Stop-Grant State, SMI#, INIT# and LINT[1:0] will be latched by the processor, and
only serviced when the processor returns to the Normal State. Only one occurrence of each event
will be recognized upon return to the Normal state.
While in Stop-Grant state, the processor will process snoops on the FSB and it will latch interrupts
delivered on the FSB.
The PBE# signal can be driven when the processor is in Stop-Grant state. PBE# will be asserted if
there is any pending interrupt latched within the processor. Pending interrupts that are blocked by
the EFLAGS.IF bit being clear will still cause assertion of PBE#. Assertion of PBE# indicates to
system logic that it should return the processor to the Normal state.
2.1.4HALT/Grant Snoop State
The processor responds to snoop or interrupt transactions on the FSB while in Stop-Grant state or
in AutoHALT Power-Down state. During a snoop or interrupt transaction, the processor enters the
HALT/Grant Snoop state. The processor will stay in this state until the snoop on the FSB has been
serviced (whether by the processor or another agent on the FSB) or the interrupt has been latched.
After the snoop is serviced or the interrupt is latched, the processor will return to the Stop-Grant
state or AutoHALT Power-Down state, as appropriate.
12Datasheet
2.1.5Sleep State
A low power state in which the processor maintains its context, maintains the phase-locked loop
(PLL), and has stopped all internal clocks. The Sleep state can be entered only from Stop-Grant
state. Once in the Stop-Grant state, the processor will enter the Sleep state upon the assertion of the
SLP# signal. The SLP# pin should only be asserted when the processor is in the Stop Grant state.
SLP# assertions while the processor is not in the Stop-Grant state is out of specification and may
result in unapproved operation.
Snoop events that occur while in Sleep State or during a transition into or out of Sleep state will
cause unpredictable behavior.
In the Sleep state, the processor is incapable of responding to snoop transactions or latching
interrupt signals. No transitions or assertions of signals (with the exception of SLP#, DPSLP# or
RESET#) are allowed on the FSB while the processor is in Sleep state. Any transition on an input
signal before the processor has returned to Stop-Grant state will result in unpredictable behavior.
If RESET# is driven active while the processor is in the Sleep state, and held active as specified in
the RESET# pin specification, then the processor will reset itself, ignoring the transition through
Stop-Grant State. If RESET# is driven active while the processor is in the Sleep State, the SLP#
and STPCLK# signals should be deasserted immediately after RESET# is asserted to ensure the
processor correctly executes the reset sequence.
Low Power Features
While in the Sleep state, the processor is capable of entering an even lower power state, the Deep
Sleep state by asserting the DPSLP# pin. (See Section 2.1.6.) While the processor is in the Sleep
state, the SLP# pin must be deasserted if another asynchronous FSB event needs to occur.
2.1.6Deep Sleep State
Deep Sleep state is a very low power state the processor can enter while maintaining context. Deep
Sleep state is entered by asserting the DPSLP# pin while in the Sleep state. BCLK may be stopped
during the Deep Sleep state for additional platform level power savings.
BCLK stop/restart timings on 855PM and Intel 855GM chipset-based platforms are as follows:
• Deep Sleep entry - DPSLP# and CPU_STP# are asserted simultaneously. The platform clock
chip will stop/tristate BCLK within 2 BCLKs +/- a few nanoseconds.
• Deep Sleep exit - DPSLP# and CPU_STP# are deasserted simultaneously. The platform clock
chip will drive BCLK to differential DC levels within 2-3 ns and starts toggling BCLK 2-6
BCLK periods later.
To re-enter the Sleep state, the DPSLP# pin must be deasserted. BCLK can be restarted after
DPSLP# deassertion, as described above. A period of 30 microseconds (to allow for PLL
stabilization) must occur before the processor can be considered to be in the Sleep State. Once in
the Sleep state, the SLP# pin must be deasserted to re-enter the Stop-Grant state.
While in Deep Sleep state, the processor is incapable of responding to snoop transactions or
latching interrupt signals. No transitions of signals are allowed on the FSB while the processor is in
Deep Sleep state. Any transition on an input signal before the processor has returned to Stop-Grant
state will result in unpredictable behavior.
When the processor is in Deep Sleep state, it will not respond to interrupts or snoop transactions.
Datasheet 13
Low Power Features
2.1.7Deeper Sleep State
The Deeper Sleep state is the lowest power state the processor can enter. This state is functionally
identical to the Deep Sleep state but at a lower core voltage. The control signals to the voltage
regulator to initiate a transition to the Deeper Sleep state are provided on the platform. Please refer
to the platform design guides listed in Table 1-1.
2.2Enhanced Intel SpeedStep® Technology
The Pentium M processor features Enhanced Intel SpeedStep technology. Unlike previous
implementations of Intel SpeedStep technology, this technology enables the processor to switch
between multiple frequency and voltage points instead of two. This will enable superior
performance with optimal power savings. Switching between states is software controlled un like
previous implementations where the GHI# pin is used to toggle between two states. Following are
the key features of Enhanced Intel SpeedStep technology:
• Multiple voltage/frequency operating points provide optimal performance at the lowest power.
• Voltage/Frequency selection is software controlled by writing to processor MSR’s (Model
Specific Registers) thus eliminating chipset dependency.
— If the target frequency is higher than the current frequency, Vcc is ramped up by placing a
new value on the VID pins and the PLL then locks to the new frequency.
— If the target frequency is lower than the current frequency, the PLL locks to the new
frequency and the Vcc is changed through the VID pin mechanism.
— Software transitions are accepted at any time. If a previous transition is in progress, the
new transition is deferred until its completion.
• The processor controls voltage ramp rates internally to ensure glitch free transitions.
• Low transition latency and large number of transitions possible per second.
— Processor core (including L2 cache) is unavailable for up to 10 s during the frequency
transition
— The bus protocol (BNR# mechanism) is used to block snooping
• No bus master arbiter disable required prior to transition and no processor cache flush
necessary.
• Improved Intel
— When the on-die thermal sensor indicates that the die temperature is too high, the
processor can automatically perform a transition to a lower frequency/voltage specified in
a software programmable MSR.
— The processor waits for a fixed time period. If the die temperature is down to acceptable
levels, an up transition to the previous frequency/voltage point occurs.
— An interrupt is generated for the up and down Intel Thermal Monitor transitions enabling
better system level thermal management.
®
Thermal Monitor mode.
14Datasheet
2.3Front Side Bus Low Power Enhancements
The Pentium M processor incorporates the following front side bus (processor system bus) low
power enhancements:
• Dynamic FSB Power Down
• BPRI# control for address and control input buffers
• Dynamic On Die Termination disabling
• Low VCCP (I/O termination voltage)
The Pentium M processor incorporates the DPWR# signal that controls the data bus input buffers
on the processor. The DPWR# signal disables the buffers when not used and activates them only
when data bus activity occurs, resulting in significant power savings with no performance impact.
BPRI# control also allows the processor address and control input buffers to be turned off when the
BPRI# signal is inactive. The on-die termination on the processor FSB buffers is disabled when the
signals are driven low, resulting in additional power savings. The low I/O termination voltage is on
a dedicated voltage plane independent of the core voltage, enabling low I/O switching power at all
times.
2.4Processor Power Status Indicator (PSI#) Signal
Low Power Features
The Pentium M processor incorporates the PSI# signal that is asserted when the processor is in a
low power (Deep Sleep or Deeper Sleep) state. This signal is asserted upon Deep Sleep entry and
deasserted upon exit. PSI# can be used to improve the light load efficiency of the voltage regulator,
resulting in platform power savings and ext ended battery life. PSI# can also be used to simplify
voltage regulator designs since it removes the need for integrated 100 s timers required to mask
the PWRGOOD signal during Deeper Sleep transitions. It also helps loosen PWRGOOD
monitoring requirements in the Deeper Sleep state.
§
Datasheet 15
Low Power Features
16Datasheet
Electrical Specifications
3Electrical Specifications
3.1Power and Ground Pins
For clean, on-chip power distribution, the Pentium M processor has a large number of VCC (power)
and V
must be connected to system ground planes. Use of multiple power and ground planes is
recommended to reduce I*R drop. Please refer to the platform design guides for more details. The
processor V
3.1.1FSB Clock (BCLK[1:0]) and Processor Clocking
BCLK[1:0] directly controls the system bus interface speed as well as the core frequency of the
processor. As in previous generation processors, the Pentium M processor core frequency is a
multiple of the BCLK[1:0] frequency. In regards to processor clocking, the Pentium M processor
uses a differential clocking implementation.
(ground) inputs. All power pins must be connected to V
SS
pins must be supplied the voltage determined by the VID (Voltage ID) pins.
CC
power planes while all VSS pins
CC
3.2Voltage Identification
The Pentium M processor uses six voltage identification pins, VID[5:0], to support automatic
selection of power supply voltages. The VID pins for the Pentium
driven by the processor VID circuitry. Table 3-1 specifies the voltage level corresponding to the
state of VID[5:0]. A “1” in this refers to a high-voltage level and a “0” refers to low-voltage level.
The Pentium M processor supports the THERMTRIP# signal for catastrophic thermal protection.
An external thermal sensor should also be used to protect the processor and the system against
excessive temperatures. Even with the activation of THERMTRIP#, which halts all processor
internal clocks and activity, leakage current can be high enough such that the processor cannot be
protected in all conditions without the removal of power to the processor. If the external thermal
sensor detects a catastrophic processor temperature of 125 °C (maximum), or if the THERMTRIP#
signal is asserted, the VCC supply to the processor must be turned off within 500 ms to prevent
permanent silicon damage due to thermal runaway.
18Datasheet
3.4Signal Terminations and Unused Pins
All RSVD (RESERVED) pins must remain unconnected. Connection of these pins to VCC, VSS, or
to any other signal (including each other) can result in component malfunction or incompatibility
with future Pentium M processors. See Section 4.2 for a pin listing of the processor and the
location of all RSVD pins.
For reliable operation, always connect unused inputs or bidirectional sign als to an appropriate
signal level. Unused active low AG TL+ inputs may be left as no connects if AGTL+ termination is
provided on the processor silicon. Unused active high inputs should be connected through a resistor
to ground (V
For details on signal terminations, please refer to the platform design guides.
). Unused outputs can be left unconnected.
SS
Electrical Specifications
The TEST1 and TEST2 pins must have a stuffing option connection to V
pull-down resistors.
separately via 1-k
SS
3.5FSB Frequency Select Signals (BSEL[1:0])
These signals are used to select the FSB clock frequency. They should be connected between the
processor and the chipset MCH and clock generator on Intel 915 Express chipset family based
platforms. These signals must be left unconnected on platforms designed with the Intel 855 chipset
family. On these platforms, FSB clock frequency should be configured on the motherboard.
3.6FSB Signal Groups
In order to simplify the following discussion, the FSB signals have been combined in to groups by
buffer type. AG TL+ input signals have differential input buffers, which use GTLREF as a reference
level. In this document, the term "AGTL+ Input" refers to the AGTL+ input grou p as well as the
AGTL+ I/O group when receiving. Similarly, "AGTL+ Output" refers to the AGTL+ output group
as well as the AGTL+ I/O group when driving.
With the implementation of a source synchronous data bus comes the need to specify two sets of
timing parameters. One set is for common clock signals which are dependant upon the rising edge
of BCLK0 (ADS#, HIT#, HITM#, etc.) and the second set is for the source synchronous signals
which are relative to their respective strobe lines (data and address) as well as the rising edge of
BCLK0. Asychronous signals are still present (A20M#, IGNNE#, etc.) and can become active at
any time during the clock cycle. Table 3-2 identifies which signals are common clock, source
synchronous, and asynchronous.
1. Refer to Chapter 4 for signal descriptions and termination requirements.
2. BPM[2:0}# and PRDY# are AGTL+ output only signals.
3. In processor systems where there is no debug port implemented on the system board, these signals are used
to support a debug port interposer. In systems with the debug port implemented on the system board, these
signals are no connects.
3.7CMOS Signals
CMOS input signals are shown in Table 3-2. Legacy output FERR#, IERR# and other non-AGTL+
signals (THERMTRIP# and PROCHOT#) utilize Open Drain output buffers. These signals do not
have setup or hold time specifications in relation to BCLK[1:0]. However, all of the CMOS signals
are required to be asserted for at least three BCLKs in order for the processor to recognize them.
See Section 3.9 for the DC and AC specifications for the CMOS signal groups.
20Datasheet
3.8Maximum Ratings
Table 3-3 lists the processor’s maximum environmental stress ratings. The processor should not
receive a clock while subjected to these conditions. Functional operating parameters are listed in
the AC and DC tables. Extended exposure to the maximum ratings may affect device reliability.
Furthermore, although the processor contains protective circuitry to resist damage from electro
static discharge (ESD), one should always take precautions to avoid high static voltages or electric
fields.
Table 3-3. Processor DC Absolute Maximum Ratings
SymbolParameterMinMax UnitNotes
T
STORAGEProcessor storage
V
CC
V
inAGTL+
V
inAsynch_CMOS
temperature
Any processor supply
voltage with respect to V
AGTL+ buffer DC input
voltage with respect to V
CMOS buffer DC input
voltage with respect to V
SS
SS
SS
Electrical Specifications
-40 85°C2
-0.31.6V1
-0.11.6V1, 2
-0.11.6V1, 2
NOTES:
1. This rating applies to any processor pin.
2. Contact Intel for storage requirements in excess of one year.
3.9Processor DC Specifications
The processor DC specifications in this section are defined at the process or core (pads) unless
noted otherwise. See Table 4-3 for the pin signal definitions and signal pin assignments. The DC
specifications for these signals are listed in Table 3-24 and Table 3-25.
Table 3-4 through Table 3-25 list the DC specifications for the Pentium
only while meeting specifications for junction temp erature, clock frequency, and input voltages.
The Highest Frequency mode (HFM) and Lowest Frequency mode (LFM) refer to the highest and
lowest core operating frequencies supported on the processor. Active mode load line s pecifications
apply in all states except in the Deep Sleep and Deeper Sleep states. V
voltage driven by the voltage regulator at power up in order to set the VID values. Unless specified
otherwise, all specifications for the Pentium M processor are at Tjunction = 100° C. Care should be
taken to read all notes associated with each parameter.
M processor and are valid
CC,BOOT
is the default
Datasheet 21
Electrical Specifications
Table 3-4. Voltage and Current Specifications - Standard Voltage Processors (Sheet 1 of 2)
1. The typical values shown are the VID encoded voltages. Static and ripple tolerances (for minimum and
maximum voltages) are defined in the load line tables, Table 3-8 through Table 3-21. Adherence to loadline
specifications for the Pentium M processor is required to ensure reliable processor operation.
2. The voltage specifications are assumed to be measured at a via on the motherboard’s opposite side of the
processor’s socket (or BGA) ball with a 100-MHz bandwidth oscilloscope, 1.5-pF maximum probe
capacitance, and 1-M minimum impedance. The maximum length of ground wire on the probe should be
less than 5 mm. Ensure external noise from the system is not coupled in the scope probe.
Datasheet23
Electrical Specifications
Table 3-5. Voltage and Current Specifications - Low Voltage Processors (Sheet 1 of 2)
SymbolParameterMinTypMaxUnitNote
V
CCD778
V
CCD758
Intel® Pentium® M
Processor, Low Voltage
778 Core VCC for
Enhanced Intel
SpeedStep
Pentium M Processor,
SpeedStep Technology
®
Operating Points:
758 Core VCC for
Operating Points:
Technology
1.6 GHz1.116
1.5 GHz1.116
1.4 GHz1.100
1.3 GHz1.084
1.2 GHz1.068
1.1 GHz1.052
1.0 GHz1.052
900 GHz1.036
800 MHz1.020
600 MHz0.988
Low Voltage,
Enhanced Intel
1.5 GHz1.116
1.4 GHz1.116
1.3 GHz1.100
1.2 GHz1.084
1.1 GHz1.068
1.0 GHz1.052
900 GHz1.036
800 MHz1.020
600 MHz0.988
V1, 2
V1, 2
24Datasheet
Electrical Specifications
Table 3-5. Voltage and Current Specifications - Low Voltage Processors (Sheet 2 of 2)
SymbolParameterMinTypMaxUnitNote
V
CCD738
NOTES:
1. The typical values shown are the VID encoded voltages. Static and ripple tolerances (for minimum and
maximum voltages) are defined in the load line tables, Table 3-8 through Table 3-21. Adherence to loadline
specifications for the Pentium M processor is required to ensure reliable processor operation.
2. The voltage specifications are assumed to be measured at a via on the motherboard’s opposite side of the
processor’s socket (or BGA) ball with a 100-MHz bandwidth oscilloscope, 1.5-pF maximum probe
capacitance, and 1-M minimum impedance. The maximum length of ground wire on the probe should be
less than 5 mm. Ensure external noise from the system is not coupled in the scope probe.
1. The typical values shown are the VID encoded voltages. Static and ripple tolerances (for minimum and
maximum voltages) are defined in the load line tables, Table 3-8 through Table 3-21. Adherence to loadline
specifications for the Pentium M processor is required to ensure reliable processor operation.
2. These are VID values. Individual processor VID values may be calibrated during manufacturing such that two
devices at the same speed may have different VID settings. Actual voltage supplied to the processor should
be as specified in the load lines in Figure 3-11 and Figure 3-12. Adherence to load line specifications is
required to ensure reliable processor operation.
3. The voltage specifications are assumed to be measured at a via on the motherboard’s opposite side of the
processor’s socket (or BGA) ball with a 100-MHz bandwidth oscilloscope, 1.5-pF maximum probe
capacitance, and 1-M minimum impedance. The maximum length of ground wire on the probe should be
less than 5 mm. Ensure external noise from the system is not coupled in the scope probe.
4. For 733J, CPU signature = 06D8h.
V1, 3
V1, 3
Datasheet27
Electrical Specifications
Table 3-7. Voltage and Current Specifications (Continued) (Sheet 1 of 3)
SymbolParameterMinTypMaxUnitNote
V
CC,BOOT
V
CCP
V
CCA
for
V
CCA
778, 758,
738 and
753,733J,
733, 723
V
CCDPRS
LP,TR1
V
CCDPRS
LP,ST1
V
CCDPRS
LP,TR2
V
CCDPRS
LP,ST2
I
CCDESICC
I
CC
Default V
Initial Power-Up
AGTL+ Termination
Voltage for
CC
1.141.201.26V2
0.9971.051.102V2
voltage
PLL Supply Voltage1.711.81.89V2,
PLL Supply Voltage for
V2, 8
Pentium M Processors
778/758/738 1.711.81.89
753/733J/733/7231.4251.51.575
Transient Deeper Sleep
0.6950.7480.795V2
Voltage
Static Deeper Sleep
0.7050.7480.785V2
Voltage
Transient Deeper Sleep
0.6690.7260.783V2, 9
Voltage
Static Deeper Sleep
0.6790.7260.793V2, 9
Voltage
for Pentium M
25A5
Processors
Recommended Design
Target
ICC for Pentium M
A3, 10
Processors:
765/755/745/778/758/738/
8.1
735/725/715 at LFM Vcc
765/755/745/735/725/715
21.0
at HFM Vcc
778/758/738 at HFM Vcc12.0
773/753/733J/733/723 at
4.0
LFM Vcc
773/753/733J at HFM Vcc7.5
773/733/723 at HFM Vcc7.0
28Datasheet
Electrical Specifications
Table 3-7. Voltage and Current Specifications (Continued) (Sheet 2 of 3)
SymbolParameterMinTypMaxUnitNote
I
AH,
I
SGNT
I
SLP
I
DSLP
ICC Auto-Halt & StopGrant for Pentium M
Processors:
765/755/745/778/758/738/
6.0
735/725/715 at LFM Vcc
765/755/745/735/725/715
15.1
at HFM Vcc
778/758/738 at HFM Vcc6.4
773/753/733J at LFM Vcc2.3
733/723 at LFM Vcc2.1
773/753/733J HFM Vcc3.3
733/723 at HFM Vcc3.1
ICC Sleep for Pentium M
Processors:
765/755/745/778/758/738/
5.9
735/725/715 at LFM Vcc
765/755/745/735/725/715
14.8
at HFM Vcc
778/758/738 at HFM Vcc6.2
773/753/733J at LFM Vcc2.2
733/723 at LFM Vcc2.0
773/753/733J at HFM Vcc3.2
733/723 at HFM Vcc3.0
ICC Deep Sleep for
Pentium M Processors:
765/755/745/778/758/738/
5.8
735/725/715 at LFM Vcc
765/755/745/735/725/715
14.2
at HFM Vcc
778/758/738 at HFM Vcc5.7
773/753/733J at LFM Vcc2.1
733/723 at LFM Vcc1.9
773/753/733J at HFM Vcc2.9
733/723 at HFM Vcc2.7
A4, 10
A4, 10
A4, 10
Datasheet29
Electrical Specifications
Table 3-7. Voltage and Current Specifications (Continued) (Sheet 3 of 3)
SymbolParameterMinTypMaxUnitNote
I
DPRSLP1ICC
Deeper Sleep @
0.748 V for Pentium M
A4, 9, 10
Processors:
765/755/745/778/758/738/
2.5
735/725/715
753/733J/733/7231.6
I
DPRSLP1ICC
Deeper Sleep @
0.726 V for Pentium M
A4, 9, 10
Processors:
765/755/745/778/758/738/
2.3
735/725/715
753/733J/733/7231.3
dI
I
CCA
I
CCP
CC/DT
V
power supply current
CC
slew rate
ICC for V
ICC for V
supply120mA
CCA
supply2.5A
CCP
0.5A/ns6, 7
NOTES:
1. The typical values shown are the VID encoded voltages. Static and ripple tolerances (for minimum and
maximum voltages) are defined in the load line tables i.e., Table 3-8 through Table 3-21. Adherence to
loadline specifications for the Pentium M processor is required to ensure reliable processor operation.
2. The voltage specifications are assumed to be measured at a via on the motherboard’s opposite side of the
processor’s socket (or BGA) ball with a 100-MHz bandwidth oscilloscope, 1.5-pF maximum probe
capacitance, and 1-Mohm minimum impedance. The maximum length of ground wire on the probe should be
less than 5 mm. Ensure external noise from the system is not coupled in the scope probe.
3. Specified at V
4. Specified at the VID voltage.
5. The I
CCDES
designed to this specification.
CC,STATIC
(max) specification comprehends future processor HFM frequencies. Platforms should be
(nominal) under maximum signal loading conditions.
6. Based on simulations and averaged over the duration of any change in current. Specified by design/
characterization at nominal V
7. Measured at the bulk capacitors on the motherboard.
. Not 100% tested.
CC
8. Pentium M processors LV and ULV will support VCCA supply voltages of both 1.8 V ±5% and1.5 V ±5%.
9. Deeper sleep voltage of 0.726 V (typical) is supported on LV and ULV Pentium M processors with C PU
signature =06D8h. A typical voltage setting between 0.726 V and 0.748 V may be used but the minimum and
maximum voltages specified in Table 3-7 should not be exceeded.
10.For 733J, CPU signature = 06D8h.
30Datasheet
Electrical Specifications
Table 3-8. Voltage Tolerances for the Intel® Pentium® M Processor (Active State) VID#A
MODE
ACTIVE
Highest Frequency Mode: VID=1.340V, Offset=0%Lowest Frequency Mode: VID=0.988V, Offset=0%
Input Low Voltage0V
Input High Voltage0.6600.7100.850V
Crossing Voltage0.250.350.55V2
Range of Crossing PointsN/AN/A0.140V6
Threshold RegionV
-0.100V
CROSS
+0.100V3
CROSS
CpadPad Capacitance1.82.32.75pF5
NOTES:
1. Unless otherwise noted, all specifications in this table apply to all processor frequencies.
2. Crossing Voltage is defined as absolute voltage where rising edge of BCLK0 is equal to the falling edge of
BCLK1.
3. Threshold Region is defined as a region entered about the crossing voltage in which the differential receiver
switches. It includes input threshold hysteresis.
4. For Vin between 0 V and V
5. Cpad includes die capacitance only. No package parasitics are included.
.
H
6. VCROSS is defined as the total variation of all crossing voltages as defined in note 2
1. Unless otherwise noted, all specifications in this table apply to all processor frequencies.
IL is defined as the maximum voltage level at a receiving agent that will be interpreted as a logical low value.
2. V
IH is defined as the minimum voltage level at a receiving agent that will be interpreted as a logical high
3. V
value.
IH and VOH may experience excursions above VCCP. However, input signal drivers must comply with the
4. V
signal quality specifications in Chapter 3.
5. This is the pull down driver resistance. Refer to processor I/O buffer models for I/V characteristics. Measured
at 0.31*VCCP. R
6. GTLREF should be generated from VCCP with a 1% tolerance resistor divider . The VCCP referred to in these
specifications is the instantaneous VCCP.
7. R
TT
0.31*VCCP. R
8. Specified with on die R
9. Cpad includes die capacitance only. No package parasitics are included.
Termination Resistance475563 7
TT
(min) = 0.38*R
ON
TT,
R
(typ) = 0.45*R
ON
is the on-die termination resistance measured at VOL of the AGTL+ output driver. Measured at
is connected to VCCP on die. Refer to processor I/O buffer models for I/V characteristics.
TT
TT
and R
are turned off.
ON
TT,
R
ON
Electrical Specifications
(max) = 0.52*R
TT.
1
5
Table 3-24. CMOS Signal Group DC Specifications
SymbolParameterMinTypMaxUnit Notes
VCCPI/O Voltage0.9971.051.102V
ILInput Low Voltage
V
IHInput High Voltage0.7*VCCPVCCP+0.1V2
V
OLOutput Low Voltage-0.100.1*VCCPV2
V
OHOutput High Voltage0.9*VCCPVCCPVCCP+0.1V2
V
OLOutput Low Current1.494.08mA4
I
OHOutput High Current1.494.08mA5
I
I
LI
CpadPad Capacitance1.02.33.0pF
NOTES:
1. Unless otherwise noted, all specifications in this table apply to all processor frequencies.
2. The VCCP referred to in these specifications refers to instantaneous VCCP.
3. Refer to the processor I/O buffer models for I/V characteristics.
4. Measured at 0.1*VCCP.
5. Measured at 0.9*VCCP.
6. For Vin between 0 V and VCCP. Measured when the driver is tristated.
7. Cpad includes die capacitance only. No package parasitics are included
CMOS
Leakage Current± 100µA6
1
-0.10.3*VCCPV2, 3
Datasheet45
Electrical Specifications
Table 3-25. Open Drain Signal Group DC Specifications
SymbolParameterMinTypMaxUnit Notes
VOHOutput High VoltageVCCPV3
OLOutput Low Voltage00.20V
V
OLOutput Low Current1650mA2
I
I
LO
CpadPad Capacitance1.72.33.0pF5
1. Unless otherwise noted, all specifications in this table apply to all processor frequencies.
2. Measured at 0.2 V.
is determined by value of the external pullup resistor to VCCP. Please refer to the platform design guides
3. V
OH
for details.
4. For Vin between 0 V and V
5. Cpad includes die capacitance only. No package parasitics are included.
Leakage Current± 200µA4
.
OH
1
§
46Datasheet
Package Mechanical Specifications and Pin Information
4Package Mechanical
Specifications and Pin Information
The Pentium M Processor is available in 478-pin, Micro-FCPGA and 479-ball, Micro-FCBGA
packages. Different views of the Micro-FCPGA package are shown in Figure 4-1 through
Figure 4-3. Package dimensions are shown in Table 4-1. Different views of the Micro-FCBGA
package are shown in Figure 4-4 through Figure 4-6. Package dimensions are shown in Table 4-2.
The Micro-FCBGA package may have capacitors placed in the area surrounding the die. Because
the die-side capacitors are electrically conductive, and only slightly shorter than the die height, care
should be taken to avoid contacting the capacitors with electrically conductive materials. Doing so
may short the capacitors, and possibly damage the device or render it inactive. The use of an
insulating material between the capacitors and any thermal solution should be considered to
prevent capacitor shorting.
Figure 4-1. Micro-FCPGA Package Top and Bottom Isometric Views
PACKAGE KEEPOUT
CAPACITOR AREA
DIE
LABEL
TOP VIEWBOTT OM VIEW
NOTE: All dimensions in millimeters. Values shown for reference only. Refer to Table 4-1 for details.
Datasheet47
Package Mechanical Specifications and Pin Information
Figure 4-2. Micro-FCPGA Package - Top and Side Views
7 (K1)
7 (K1)
8 places
8 places
D1
D1
5 (K)
5 (K)
4 places
4 places
SUBSTRATE KEEPOUT ZONE
SUBSTRATE KEEPOUT ZONE
DO NOT CONTACT PACKAGE
DO NOT CONTACT PACKAGE
IN S ID E T HIS LINE
IN S ID E T HIS LINE
35 (D)
35 (D)
0.286
0.286 0.286
A
A
1.25 MAX
1.25 MAX
(A3)
(A3)
Ø 0.32 (B)
Ø 0.32 (B)
478 places
478 places
A2
E1
E1
35 (E)
35 (E)
A2
PIN A1 CORNER
PIN A1 CORNER
2.03 ±0.08
2.03 ±0.08
(A1)
(A1)
NOTE: MDie is centered on the Package. All dimensions in millimeters. Values shown for reference only. Refer
to Table 4-1 for details.
48Datasheet
Package Mechanical Specifications and Pin Information
Figure 4-3. Micro-FCPGA Package - Bottom View
AF
AE
AD
AC
AB
AA
Y
W
V
U
T
R
P
N
M
L
K
J
H
G
F
E
D
C
B
A
25X 1.27
(e)
1
57911
2346810 12 14 16 18
25X 1.27
(e)
14 (K3)
13 15 17
19 21 23 25
22 24 26
20
14 (K3)
NOTE: All dimensions in millimeters. Values shown for reference only. Refer to Table 4-1 for details.
Datasheet 49
Package Mechanical Specifications and Pin Information
Table 4-1. Micro-FCPGA Package Dimensions
SymbolParameterMinMaxUnit
AOverall height, top of die to package seating plane1.882.02mm
–Overall height, top of die to PCB surface, including
PdieAllowable pressure on the die for thermal solution–689kPa
WPackage weight4.5g
Package Surface Flatness
4.745.16mm
0.286mm
NOTE: Overall height with socket is based on design dimensions of the Micro-FCPGA package with no thermal
solution attached. Values are based on design specifications and tolerances. This dimension is subject
to change based on socket design, OEM motherboard design or OEM SMT process.
50Datasheet
Package Mechanical Specifications and Pin Information
Figure 4-4. Micro-FCBGA Package Top and Bottom Isometric Views
PACKAGE KEEPOUT
CAPACITOR AREA
LABEL
DIE
TOP VIEWBOTTOM VIEW
Datasheet51
Package Mechanical Specifications and Pin Information
Figure 4-5. Micro-FCBGA Package Top and Side Views
7 (K1)
8 places
D1
5 (K)
4 places
E1
SUBSTRATE KEEPOUT ZONE
DO NOT CONTACT PACKAGE
INSIDE T HIS LI NE
35 (D)
A2
K2
0.20
A
Ø 0.78 (b)
479 places
35 (E)
NOTE: Die is centered on the Package. All dimensions in millimeters. Values shown for reference only . Refer to
Table 4-2 for details.
PIN A1 CORNER
52Datasheet
Package Mechanical Specifications and Pin Information
Table 4-2. Micro-FCBGA Package Dimensions
SymbolParameterMinMaxUnit
AOverall height, as delivered (Refer to Note 1)2.602.85mm
Package Mechanical Specifications and Pin Information
4.2Alphabetical Signals Reference
Table 4-5. Signal Description (Sheet 1 of 7)
NameTypeDescription
A[31:3]#Input/
Output
A20M#InputIf A20M# (Address-20 Mask) is asserted, the processor masks physical address
ADS#Input/
Output
ADSTB[1:0]#Input/
Output
A[31:3]# (Address) define a 2
phase 1 of the address phase, these pins transmit the address of a transaction.
In sub-phase 2, these pins transmit transaction type information. These signals
must connect the appropriate pins of both agents on the Intel
Processor FSB. A[31:3]# are source synchronous signals and are latched into
the receiving buffers by ADSTB[1:0]#. Address signals are used as straps which
are sampled before RESET# is deasserted.
bit 20 (A20#) before looking up a line in any internal cache and before driving a
read/write transaction on the bus. Asserting A20M# emulates the 8086
processor's address wrap-around at the 1-Mbyte boundary. Assertion of A20M#
is only supported in real mode.
A20M# is an asynchronous signal. However, to ensure recognition of this signal
following an Input/Output write instruction, it must be valid along with the TRDY#
assertion of the corresponding Input/Output Write bus transaction.
ADS# (Address Strobe) is asserted to indicate the validity of the transaction
address on the A[31:3]# and REQ[4:0]# pins. All bus agents observe the ADS#
activation to begin parity checking, protocol checking, address decode, internal
snoop, or deferred reply ID match operations associated with the new
transaction.
Address strobes are used to latch A[31:3]# and REQ[4:0]# on their rising and
falling edges. Strobes are associated with signals as shown below.
32
-byte physical memory address space. In sub-
®
Pentium® M
SignalsAssociated Strobe
REQ[4:0]#, A[16:3]# ADSTB[0]#
A[31:17]#ADSTB[1]#
BCLK[1:0]InputThe differential pair BCLK (Bus Clock) determines the FSB frequency. All FSB
BNR#Input/
BPM[2:0]#
BPM[3]
BPRI#InputBPRI# (Bus Priority Request) is used to arbitrate for ownership of the FSB. It
BR0#Input/
Output
Output
Input/
Output
Output
agents must receive these signals to drive their outputs and latch their inputs.
All external timing parameters are specified with respect to the rising edge of
BCLK0 crossing V
BNR# (Block Next Request) is used to assert a bus stall by any bus agent who is
unable to accept new bus transactions. During a bus stall, the current bus owner
cannot issue any new transactions.
BPM[3:0]# (Breakpoint Monitor) are breakpoint and performance monitor
signals. They are outputs from the processor which indicate the status of
breakpoints and programmable counters used for monitoring processor
performance. BPM[3:0]# should connect the appropriate pins of all Intel
®
Pentium
Please refer to the platform design guides for
must connect the appropriate pins of both FSB agents. Observing BPRI# active
(as asserted by the priority agent) causes the other agent to stop issuing new
requests, unless such requests are part of an ongoing locked operation. The
priority agent keeps BPRI# asserted until all of its requests are completed, then
releases the bus by deasserting BPRI#.
BR0# is used by the processor to request the bus. The arbitration is done
between Intel
MCH-M (High Priority Agent).
M FSB agents.This includes debug or performance monitoring tools.
®
Pentium® M (Symmetric Agent) and Intel 855 chipset family
CROSS
.
®
more detailed information.
70Datasheet
Package Mechanical Specifications and Pin Information
Table 4-5. Signal Description (Sheet 2 of 7)
NameTypeDescription
BSEL[1:0]OutputThese signals are used to select the FSB clock frequency. They should be
COMP[3:0]AnalogCOMP[3:0] must be terminated on the system board using precision (1%
D[63:0]#Input/
Output
connected between the processor and the chipset MCH and clock generator on
Intel 915 chipset family based platforms. These signals must be left
unconnected on platforms designed with the Intel 855 chipset family. On these
platforms, FSB clock frequency should be configured on the motherboard.
tolerance) resistors. Refer to the platform design guides for more details on
implementation.
D[63:0]# (Data) are the data signals. These signals provide a 64-bit data path
between the FSB agents, and must connect the appropriate pins on both agents.
The data driver asserts DRDY# to indicate a valid data transfer.
D[63:0]# are quad-pumped signals and will thus be driven four times in a
common clock period. D[63:0]# are latched off the falling edge of both
DSTBP[3:0]# and DSTBN[3:0]#. Each group of 16 data signals correspond to a
pair of one DSTBP# and one DSTBN#. The following table shows the grouping
of data signals to data strobes and DINV#
Quad-Pumped Signal Groups
.
Data Group
D[15:0]#00
D[31:16]#11
D[47:32]#22
D[63:48]#33
Furthermore, the DINV# pins determine the polarity of the data signals. Each
group of 16 data signals corresponds to one DINV# signal. When the DINV#
signal is active, the corresponding data group is inverted and therefore sampled
active high.
DBR#OutputDBR# (Data Bus Reset) is used only in processor systems where no debug port
DBSY#Input/
Output
DEFER#InputDEFER# is asserted by an agent to indicate that a transaction cannot be
is implemented on the system board. DBR# is used by a debug port interposer
so that an in-target probe can drive system reset. If a debug port is implemented
in the system, DBR# is a no connect in the system. DBR# is not a processor
signal.
DBSY# (Data Bus Busy) is asserted by the agent responsible for driving data on
the FSB to indicate that the data bus is in use. The data bus is released after
DBSY# is deasserted. This signal must connect the appropriate pins on both
FSB agents.
guaranteed in-order completion. Assertion of DEFER# is normally the
responsibility of the addressed memory or Input/Output agent. This signal must
connect the appropriate pins of both FSB agents.
DSTBN#/
DSTBP#
DINV#
Datasheet71
Package Mechanical Specifications and Pin Information
Table 4-5. Signal Description (Sheet 3 of 7)
NameTypeDescription
DINV[3:0]#Input/
Output
DINV[3:0]# (Data Bus Inversion) are source synchronous and indicate the
polarity of the D[63:0]# signals. The DINV[3:0]# signals are activated when the
data on the data bus is inverted. The bus agent will invert the data bus signals if
more than half the bits, within the covered group, would change level in the next
cycle.
DPSLP#InputDPSLP# when asserted on the platform causes the processor to transition from
DPWR#InputDPWR# is a control signal from the Intel
DRDY#Input/
Output
DSTBN[3:0]#Input/
Output
DSTBP[3:0]#Input/
Output
the Sleep State to the Deep Sleep state. In order to return to the Sleep state,
DPSLP# must be deasserted. DPSLP# is driven by the ICH4-M component and
also connects to the Intel 855 chipset family MCH-M component.
®
®
to reduce power on the Intel
DRDY# (Data Ready) is asserted by the data driver on each data transfer,
indicating valid data on the data bus. In a multi-common clock data transfer,
DRDY# may be deasserted to insert idle clocks. This signal must connect the
appropriate pins of both FSB agents.
Package Mechanical Specifications and Pin Information
Table 4-5. Signal Description (Sheet 4 of 7)
NameTypeDescription
FERR#/PBE#OutputFERR# (Floating-point Error)PBE#(Pending Break Event) is a multiplexed signal
GTLREFInputGTLREF determines the signal reference level for AGTL+ input pins. GTLREF
HIT#
HITM#
IERR#OutputIERR# (Internal Error) is asserted by a processor as the result of an internal
IGNNE#InputIGNNE# (Ignore Numeric Error) is asserted to force the processor to ignore a
INIT#InputINIT# (Initialization), when asserted, resets integer registers inside the processor
ITP_CLK[1:0]InputITP_CLK[1:0] are copies of BCLK that are used only in processor systems
Input/
Output
Input/
Output
and its meaning is qualified with STPCLK#. When STPCLK# is not asserted,
FERR#/PBE# indicates a floating point when the processor detects an
unmasked floating-point error. FERR# is similar to the ERROR# signal on the
Intel 387 coprocessor, and is included for compatibility with systems using MSDOS*-type floating-point error reporting. When STPCLK# is asserted, an
assertion of FERR#/PBE# indicates that the processor has a pending break
event waiting for service. The assertion of FERR#/PBE# indicates that the
processor should be returned to the Normal state. When FERR#/PBE# is
asserted, indicating a break event, it will remain asserted until STPCLK# is
deasserted. Assertion of PREQ# when STPCLK# is active will also cause an
FERR# break event.
For additional information on the pending break event functionality, including
identification of support of the feature and enable/disable information, refer to
Volume 3 of the
Processor Identification and CPUID Instruction application note.
For termination requirements please refer to the platform design guides.
should be set at 2/3 V
if a signal is a logical 0 or logical 1. Please refer to the platform design guides for
details on GTLREF implementation.
HIT# (Snoop Hit) and HITM# (Hit Modified) convey transaction snoop operation
results. Either FSB agent may assert both HIT# and HITM# together to indicate
that it requires a snoop stall, which can be continued by reasserting HIT# and
HITM# together.
error. Assertion of IERR# is usually accompanied by a SHUTDOWN transaction
on the FSB. This transaction may optionally be converted to an external error
signal (e.g., NMI) by system core logic. The processor will keep IERR# asserted
until the assertion of RESET#, BINIT#, or INIT#.
For termination requirements please refer to the platform design guides.
numeric error and continue to execute noncontrol floating-point instructions. If
IGNNE# is deasserted, the processor generates an exception on a noncontrol
floating-point instruction if a previous floating-point instruction caused an error.
IGNNE# has no effect when the NE bit in control register 0 (CR0) is set.
IGNNE# is an asynchronous signal. However, to ensure recognition of this signal
following an Input/Output write instruction, it must be valid along with the TRDY#
assertion of the corresponding Input/Output Write bus transaction.
without affecting its internal caches or floating-point registers. The processor
then begins execution at the power-on Reset vector configured during power-on
configuration. The processor continues to handle snoop requests during INIT#
assertion. INIT# is an asynchronous signal. However, to ensure recognition of
this signal following an Input/Output Write instruction, it must be valid along with
the TRDY# assertion of the corresponding Input/Output Write bus transaction.
INIT# must connect the appropriate pins of both FSB agents.
If INIT# is sampled active on the active to inactive transition of RESET#, then the
processor executes its Built-in Self-Test (BIST)
For termination requirements please refer to the platform design guides.
where no debug port is implemented on the system board. ITP_CLK[1:0] are
used as BCLK[1:0] references for a debug port implemented on an interposer. If
a debug port is implemented in the system, ITP_CLK[1:0] are no connects in the
system. These are not processor signals.
Intel Architecture Software Developer’s Manual and the Intel
. GTLREF is used by the AGTL+ receivers to determine
CCP
Datasheet73
Package Mechanical Specifications and Pin Information
Table 4-5. Signal Description (Sheet 5 of 7)
NameTypeDescription
LINT[1:0]InputLINT[1:0] (Local APIC Interrupt) must connect the appropriate pins of all APIC
LOCK#Input/
Output
PRDY#OutputProbe Ready signal used by debug tools to determine processor debug
PREQ#InputProbe Request signal used by debug tools to request debug operation of the
PROCHOT#OutputPROCHOT# (Processor Hot) will go active when the processor temperature
PSI#OutputProcessor Power Status Indicator signal. This signal is asserted when the
PWRGOODInputPWRGOOD (Power Good) is a processor input. The processor requires this
REQ[4:0]#Input/
Output
RESET#InputAsserting the RESET# signal resets the processor to a known state and
Bus agents. When the APIC is disabled, the LINT0 signal becomes INTR, a
maskable interrupt request signal, and LINT1 becomes NMI, a nonmaskable
interrupt. INTR and NMI are backward compatible with the signals of those
names on the Pentium Processor. Both signals are asynchronous.
Both of these signals must be software configured via BIOS programming of the
APIC register space to be used either as NMI/INTR or LINT[1:0]. Because the
APIC is enabled by default after reset, operation of these pins as LINT[1:0] is the
default configuration.
LOCK# indicates to the system that a transaction must occur atomically. This
signal must connect the appropriate pins of both FSB agents. For a locked
sequence of transactions, LOCK# is asserted from the beginning of the first
transaction to the end of the last transaction.
When the priority agent asserts BPRI# to arbitrate for ownership of the FSB, it
will wait until it observes LOCK# deasserted. This enables symmetric agents to
retain ownership of the FSB throughout the bus locked operation and ensure the
atomicity of lock.
readiness.
Please refer to the platform design guides for more implementation details.
processor.
Please refer to the platform design guides for more implementation details.
monitoring sensor detects that the processor has reached its maximum safe
operating temperature. This indicates that the processor Thermal Control Circuit
has been activated, if enabled. See Chapter 5 for more details.
For termination requirements please refer to the platform design guides.
This signal may require voltage translation on the motherboard. Please refer to
the platform design guides for more details.
processor is in a lower state (Deep Sleep and Deeper Sleep). See Section 2.1.6
for more details.
signal to be a clean indication that the clocks and power supplies are stable and
within their specifications. Clean implies that the signal will remain low (capable
of sinking leakage current), without glitches, from the time that the power
supplies are turned on until they come within specification. The signal must then
transition monotonically to a high state.
The PWRGOOD signal must be supplied to the processor; it is used to protect
internal circuits against voltage sequencing issues. It should be driven high
throughout boundary scan operation.
For termination requirements please refer to the platform design guides.
REQ[4:0]# (Request Command) must connect the appropriate pins of both FSB
agents. They are asserted by the current bus owner to define the currently active
transaction type. These signals are source synchronous to ADSTB[0]#.
invalidates its internal caches without writing back any of their contents. For a
power-on Reset, RESET# must stay active for at least two milliseconds after
CC and BCLK have reached their proper specifications. On observing active
V
RESET#, both FSB agents will deassert their outputs within two clocks. All
processor straps must be valid within the specified setup time before RESET# is
deasserted.
Please refer to the
implementation details. There is a 55 ohm (nominal) on die pullup resistor on this
signal.
Platform Design Guides for termination requirements and
74Datasheet
Package Mechanical Specifications and Pin Information
Table 4-5. Signal Description (Sheet 6 of 7)
NameTypeDescription
RS[2:0]#InputRS[2:0]# (Response Status) are driven by the response agent (the agent
RSVDReserved/
SLP#InputSLP# (Sleep), when asserted in Stop-Grant state, causes the processor to enter
SMI#InputSMI# (System Management Interrupt) is asserted asynchronously by system
STPCLK#InputSTPCLK# (Stop Clock), when asserted, causes the processor to enter a low
TCKInputTCK (Test Clock) provides the clock input for the processor test bus (also known
TDIInputTDI (Test Data In) transfers serial test data into the processor. TDI provides the
TDOOutputTDO (Test Data Out) transfers serial test data out of the processor. TDO
TEST1,
TEST2
THERMDAOtherThermal Diode Anode.
THERMDCOtherThermal Diode Cathode.
THERMTRIP#OutputThe processor protects itself from catastrophic overheating by use of an internal
No
Connect
InputTEST1 and TEST2 must have a stuffing option of separate pull down resistors to
responsible for completion of the current transaction), and must connect the
appropriate pins of both FSB agents.
These pins are RESERVED and must be left unconnected on the board.
However, it is recommended that routing channels to these pins on the board be
kept open for possible future use. Please refer to the platform design guides for
more details.
the Sleep state. During Sleep state, the processor stops providing internal clock
signals to all units, leaving only the Phase-Locked Loop (PLL) still operating.
Processors in this state will not recognize snoops or interrupts. The processor
will recognize only assertion of the RESET# signal, deassertion of SLP#, and
removal of the BCLK input while in Sleep state. If SLP# is deasserted, the
processor exits Sleep state and returns to Stop-Grant state, rest arting its internal
clock signals to the bus and processor core units. If DPSLP# is asserted while in
the Sleep state, the processor will exit the Sleep state and transition to the Deep
Sleep state.
logic. On accepting a System Management Interrupt, the processor saves the
current state and enter System Management mode (SMM). An SMI
Acknowledge transaction is issued, and the processor begins program execution
from the SMM handler.
If SMI# is asserted during the deassertion of RESET# the processor will tristate
its outputs.
power Stop-Grant state. The processor issues a Stop-Grant Acknowledge
transaction, and stops providing internal clock signals to all processor core units
except the FSB and APIC units. The processor continues to snoop bus
transactions and service interrupts while in Stop-Grant state. When STPCLK# is
deasserted, the processor restarts its internal clock to all units and resumes
execution. The assertion of STPCLK# has no effect on the bus clock; STPCLK#
is an asynchronous input.
as the Test Access Port).
Please refer to the platform design guides for termination requirements and
implementation details.
serial input needed for JTAG specification support.
Please refer to the platform design guides for termination requirements and
implementation details.
provides the serial output needed for JTAG specification support.
Please refer to the platform design guides for termination requirements and
implementation details.
. Please refer to the platform design guides for more details.
V
SS
thermal sensor. This sensor is set well above the normal operating temperature
to ensure that there are no false trips. The processor will stop all execution when
the junction temperature exceeds approximately 125 °C. This is signalled to the
system by the THERMTRIP# (Thermal Trip) pin.
For termination requirements please refer to the platform design guides .
Datasheet75
Package Mechanical Specifications and Pin Information
Table 4-5. Signal Description (Sheet 7 of 7)
NameTypeDescription
TMSInputTMS (Test Mode Select) is a JTAG specification support signal used by debug
TRDY#InputTRDY# (Target Ready) is asserted by the target to indicate that it is ready to
TRST#InputTRST# (Test Reset) resets the Test Access Port (TAP) logic. TRST# must be
V
CC
[3:0]InputV
V
CCA
V
CCP
[1:0]InputQuiet power supply for on die COMP circuitry. These pins should be connected
V
CCQ
V
CCSENSE
InputProcessor core power supply.
InputProcessor I/O power supply.
OutputV
VID[5:0]OutputVID[5:0] (Voltage ID) pins are used to support automatic selection of power
V
SSSENSE
OutputV
tools.
Please refer to the platform design guides for termination requirements and
implementation details.
receive a write or implicit writeback data transfer. TRDY# must connect the
appropriate pins of both FSB agents.
driven low during power on Reset. Please refer to the platform design guides for
termination requirements and implementation details.
provides isolated power for the internal processor core PLL’s. Refer to the
CCA
platform design guides for complete implementation details.
on the motherboard. However, these connections should enable addition
to V
CCP
of decoupling on the V
is an isolated low impedance connection to processor core power
CCSENSE
). It can be used to sense or measure power near the silicon with little noise.
(V
CC
Please refer to the platform design guides for termination recommendations and
CCQ
more details.
supply voltages (Vcc). Unlike some previous generations of processors, these
are CMOS signals that are driven by the Intel
voltage supply for these pins must be valid before the VR can supply Vcc to the
processor. Conversely, the VR output must be disabled until the voltage supply
for the VID pins becomes valid. The VID pins are needed to support the
processor voltage specification variations. See Table 3-1 for definitions of these
pins. The VR must supply the voltage that is requested by the pins, or disable
itself.
is an isolated low impedance connection to processor core VSS. It can
SSSENSE
be used to sense or measure ground near the silicon with little noise. Please
refer to the platform design guides for termination recommendations and more
details.
lines if necessary.
®
Pentium® M processor. The
§§
76Datasheet
Thermal Specifications and Design Considerations
5Thermal Specifications and
Design Considerations
The Pentium M Processor requires a thermal solution to maintain temperatures within operating
limits as set forth in Section 5.1. Any attempt to operate that processor outside these operating
limits may result in permanent damage to the processor and potentially other components in the
system. As processor technology changes, thermal management becomes increasingly crucial
when building computer systems. Maintaining the proper thermal environment is key to reliable,
long-term system operation. A complete thermal solution includes both component and system
level thermal management features. Component level thermal solutions include active or passive
heatsinks or heat exchangers attached to the processor exposed die. The solution should make firm
contact to the die while maintaining processor mechanical specifications such as pressure. A
typical system level thermal solution may consist of a processor fan ducted to a heat exchanger that
is thermally coupled to the processor via a heat pipe or direct die attachment. A secondary fan or air
from the processor fan may also be used to cool other platform components or lower the internal
ambient temperature within the system.
T o allow for the optimal operation and long-term reliability of Intel processor-based systems, the
system/processor thermal solution should be designed such that the processor must remain within
the minimum and maximum junction temperature (Tj) specifications at the corresponding thermal
design power (TDP) value listed in Table 5-1. Thermal solutions not design to provide this level of
thermal capability may affect the long-term reliability of the processor and system.
The maximum junction temperature is define d by an activation of the processor Intel Thermal
Monitor. Refer to Section 5.1.3 for more details. Analysis indicates that real applications are
unlikely to cause the processor to consume the theoretical maximum power dissipation for
sustained time periods. Intel recommends that complete thermal solution designs target the TDP
indicated in Table 5-1. The Intel Thermal Monitor feature is designed to help protect the processor
in the unlikely event that an application exceeds the TDP recommendation for a sustained period of
time. For more details on the usage of this feature, refer to Section 5.1.3. In all cases the Intel
Thermal Monitor feature must be enabled for the processor to remain within specification.
Datasheet 77
Thermal Specifications and Design Considerations
Table 5-1. Power Specifications for the Intel® Pentium M Processor (Sheet 1 of 3)
Table 5-1. Power Specifications for the Intel® Pentium M Processor (Sheet 2 of 3)
Symbol
P
SLP
P
DSLP
P
DPRSL
P1
Processor
Number
765/755/745/
735/725/715
ParameterMinTypMaxUnitNotes
Sleep Power:WAt 50 °C, Note 2
LFM Vcc3.2
HFM Vcc10.5
778/758/738Sleep Power:WAt 50 °C, Note 2
LFM Vcc3.2
HFM Vcc4.0
773/753/733JSleep Power:WAt 50 °C, Note 2, 5
LFM Vcc1.0
HFM Vcc1.7
733/723Sleep Power:WAt 50 °C, Note 2
LFM Vcc0.9
HFM Vcc1.7
765/755/745/
735/725/715
Deep Sleep Power:WAt 35 °C, Note 2
LFM Vcc2.5
HFM Vcc8.8
778/758/738Deep Sleep Power:WAt 35 °C, Note 2
LFM Vcc2.5
HFM Vcc2.9
773/753/733JDeep Sleep Power:WAt 35 °C, Note 2, 5
LFM Vcc0.7
HFM Vcc1.25
733/723Deep Sleep Power:WAt 35 °C, Note 2
LFM Vcc0.6
HFM Vcc1.2
765/755/745/
735/725/715 &
Deeper Sleep Power
@ 0.748V
0.8WAt 35 °C, Note 2
778/758/738
753/733J/733/
723
Deeper Sleep Power
(ULV only)@ 0.748V
0.5WAt 35 °C, Note 2, 5
Datasheet79
Thermal Specifications and Design Considerations
Table 5-1. Power Specifications for the Intel® Pentium M Processor (Sheet 3 of 3)
Symbol
P
DPRSL
P2
T
J
NOTES:
1. The Thermal Design Power (TDP) specification should be used to design the processor thermal solution. The
TDP is not the maximum theoretical power the processor can dissipate.
2. Not 100% tested. These power specifications are determined by characterization of the processor currents at
higher temperatures and extrapolating the values for the temperature indicated.
3. As measured by the on-die Intel Thermal Monitor. The Intel Thermal Monitor’s automatic mode is used to
indicate that the maximum T
4. The Intel Thermal Monitor automatic mode must be enabled for the processor to operate within
specifications.
5. For 733J, CPU Signature = 06D8h.
Processor
Number
765/755/745/
735/725/715 &
778/758/738
753/733J/733/
723
ParameterMinTypMaxUnitNotes
Deeper Sleep Power
@ 0.726V
Deeper Sleep Power
(ULV only)@ 0.726
Junction
Temperature
has been reached. Refer to Section 5.1 for more details.
J
5.1Thermal Specifications
5.1.1Thermal Diode
The Pentium M Processor incorporates two methods of monitoring die temperature, the Intel
Thermal Monitor and the thermal diode. The Intel Thermal Monitor (detailed in Section 5.1) must
be used to determine when the maximum specified processor junction temperature has been
reached. The second method, the thermal diode, can be read by an off-die analog/digital converter
(a thermal sensor) located on the motherboard, or a stand-alone measurement kit. The thermal
diode may be used to monitor the die temperature of the processor for thermal management or
instrumentation purposes but cannot be used to indicate that the maximum T
been reached. When using the thermal diode, a temperature offset value must be read from a
processor Model Specific register (MSR) and applied. See Section 5.1.2 for more details. Please
see Section 5.1.3 for thermal diode usage recommendation when the PROCHOT# signal is not
asserted. Table 5-2 and Table 5-3 provide the diode interface and specifications.
0.7WAt 35 °C, Note 2
0.4WAt 35 °C, Note 2, 5
0100CNotes 3, 4
of the processor has
J
Note: The reading of the external thermal sensor (on the motherboard) connected to the processor
thermal diode signals, will not necessarily reflect the temperature of the hottest location on the die.
This is due to inaccuracies in the external thermal sensor , on-die tempe rature gradients between the
location of the thermal diode and the hottest location on the die, and time based variations in the die
temperature measurement. Time-based variations can occur when the sampling rate of the thermal
diode (by the thermal sensor) is slower than the rate at which the T
temperature can change.
J
Offset between the thermal diode based temperature reading and the Intel Thermal Monitor reading
may be characterized using the Intel Thermal Monitor’s Automatic mode activation of thermal
control circuit. This temperature offset must be taken into account when using the processor
thermal diode to implement power management events.
80Datasheet
5.1.2Thermal Diode Offset
A temperature offset value (specified as Toffset in Table 5-3) will be programmed into a
Pentium M Processor Model Specific Register (MSR). This offset is determined by using a thermal
diode ideality factor mean value of n = 1.0022 (shown in Table 5-3) as a reference. This offset must
be applied to the junction temperature read by the thermal diode. Any temperature adjustments due
to differences between the reference ideality value of 1.0022 and the default ideality values
programmed into the on-board thermal sensors, will have to be made before the above offset is
applied.
1. Intel does not support or recommend operation of the thermal diode under reverse bias. Intel does not
support or recommend operation of the thermal diode when the processor power supplies are not within their
specified tolerance range.
2. Characterized at 100 °C.
3. Not 100% tested. Specified by design/characterization.
4. The ideality factor, n, represents the deviation from ideal diode behavior as exemplified by the diode
equation:
I
FW=Is
Where I
and T = absolute temperature (Kelvin).
Value shown in the table is not the Pentium M Processor thermal diode ideality factor. It is a reference value
used to calculate the Pentium M Processor thermal diode temperature offset.
5. The series resistance, R
temperature. R
board trace resistance between the socket and the external remote diode thermal sensor. R
remote diode thermal sensors with automatic series resistance cancellation to calibrate out this error term.
Another application is that a temperature offset can be manually calculated and programmed into an offset
register in the remote diode thermal sensors as exemplified by the equation:
T
6. Offset value is programmed in processor Model Specific Register.
Forward Bias Current5300ANote 1
offset
Factor used to calculate
temperature offset
Series Resistance3.06Ohms2, 3, 5
(qVD/nkT)
*(e
= saturation current, q = electronic charge, VD = voltage across the diode, k = Boltzmann Constant,
S
= [RT*(N-1)*I
error
-1)
, is provided to allow for a more accurate measurement of the diode junction
T
as defined includes the pins of the processor but does not include any socket resistance or
T
]/[(no/q)*ln N
FWmin
-411°C2, 6
1.0022Notes 2, 3, 4
can be used by
T
Datasheet81
Thermal Specifications and Design Considerations
5.1.3Intel® Thermal Monitor
The Intel Thermal Monitor helps control the processor temperature by activating the TCC when the
processor silicon reaches its maximum operating temperature. The temperature at which Intel
Thermal Monitor activates the thermal control circuit is not user configurable and is not software
visible. Bus traffic is snooped in the normal manner, and interrupt requests are latched (and
serviced during the time that the clocks are on) while the TCC is active.
With a properly designed and characterized thermal solution, it is anticipated that the TCC would
only be activated for very short periods of time when running the most power intensive
applications. The processor performance impact due to these brief periods of TCC activation is
expected to be so minor that it would not be detectable. An under-designed thermal solution that is
not able to prevent excessive activation of the TCC in the anticipated ambient environment may
cause a noticeable performance loss, and may affect the long-term reliability of the processor. In
addition, a thermal solution that is significantly under designed may not be capable of cooling th e
processor even when the TCC is active continuously.
The Intel Thermal Monitor controls the processor temperature by modulating (starting and
stopping) the processor core clocks or by initiating an Enhanced Intel SpeedStep technology
transition when the processor silicon reaches its maximum operating temperature. The Intel
Thermal Monitor uses two modes to activate the TCC: Automatic mode and On-Demand mode. If
both modes are activated, Automatic mode takes precedence.
Caution: The Intel Thermal Monitor Automatic Mode mst be enabled via BIOS for the processor to be
operating within specifications.
There are two automatic modes called Intel Thermal Monitor 1 and Intel Thermal Monitor 2. These
modes are selected by writing values to the Model Specific registers (MSRs) of the processor. After
Automatic mode is enabled, the TCC will activate only when the internal die temperature reaches
the maximum allowed value for operation.
Likewise, when Intel Thermal Monitor 2 is enabled, and a high temperature situation exists, the
processor will perform an Enhanced Intel SpeedStep technology transition to a lower operating
point. When the processor temperature drops below the critical level, the processor will make an
Enhanced Intel SpeedStep technology transition to the last requested operating point. Intel Thermal
Monitor 2 is the recommended mode on the Intel
®
Pentium® M processors.
If a processor load based Enhanced Intel SpeedStep technology transition (through MSR write) is
initiated when an Intel Thermal Monitor 2 period is active, there are two possible results:
1.If the processor load based Enhanced Intel SpeedStep technology transition target frequency is
higher than the Intel Thermal Monitor 2 transition based target frequency, the processor loadbased transition will be deferred until the Intel Thermal Monitor 2 event has been completed.
2.If the processor load-based Enhanced Intel SpeedStep technology transition target frequency is
lower than the Intel Thermal Monitor 2 transition based target frequency, the processor will
transition to the processor load-based Enhanced Intel SpeedStep technology target frequency
point.
When Intel Thermal Monitor 1 is enabled, and a high temperature situation exists, the clocks will
be modulated by alternately turning the clocks off and on at a 50% duty cycle. Cycle times are
processor speed dependent and will decrease linearly as processor core frequencies increase. Once
the temperature has returned to a non-critical level, modulation ceases and TCC goes inactive. A
small amount of hysteresis has been included to prevent rapid active/inactive transitions of the
TCC when the processor temperature is near the trip point. The duty cycle is factory configured
82Datasheet
Thermal Specifications and Design Considerations
and cannot be modified. Also, automatic mode does not require any additional hardware, software
drivers, or interrupt handling routines. Processor performance will be decreased by the same
amount as the duty cycle when the TCC is active, however, with a properly designed and
characterized thermal solution the TCC most likely will never be activated, or only will be
activated briefly during the most power intensive applications.
The TCC may also be activated via On-Demand mode. If bit 4 of the ACPI Intel Thermal Monitor
Control Register is written to a 1, the TCC will be activated immediately, independent of the
processor temperature. When using On-Demand mode to activate the TCC, the duty cycle of the
clock modulation is programmable via bits 3:1 of the same ACPI Intel Thermal Monitor Control
Register. In automatic mode, the duty cycle is fixed at 50% on, 50% off, however in On-Demand
mode, the duty cycle can be programmed from 12.5% on/ 87.5% off, to 87.5% on/12.5% off in
12.5% increments. On-Demand mode may be used at the same time Automatic mode is enabled,
however, if the system tries to enable the TCC via On-Demand mode at the same time automatic
mode is enabled and a high temperature condition exists, automatic mode will take precedence.
An external signal, PROCHOT# (processor hot) is asserted when the processor detects that its
temperature is above the thermal trip point. Bus snooping and interrupt latching are also active
while the TCC is active.
Besides the thermal sensor and thermal control circuit, the Intel Thermal Monitor feature also
includes one ACPI register, one performance counter register, three model specific registers
(MSR), and one I/O pin (PROCHOT#). All are available to monitor and control the state of the
Intel Thermal Monitor feature. The Intel Thermal Monitor can be configured to generate an
interrupt upon the assertion or deassertion of PROCHOT#.
Note: PROCHOT# will not be asserted when the processor is in the Stop Grant, Sleep, Deep Sleep, and
Deeper Sleep low power states (internal clocks stopped), hence the thermal diode reading must be
used as a safeguard to maintain the processor junction temperature within the 100 °C (maximum)
specification. If the platform thermal solution is not able to maintain the processor junctio n
temperature within the maximum specification, the system must initiate an orderl y shutdown to
prevent damage. If the processor enters one of the above low power states with PROCHOT#
already asserted, PROCHOT# will remain asserted until the processor exits the Low Power state
and the processor junction temperature drops below the thermal trip point.
If automatic mode is disabled, the processor will be operating out of specification. Regardless of
enabling the automatic or On-Demand modes, in the event of a catastrophic cooling failure, the
processor will automatically shut down when the silicon has reached a temperature of
approximately 125 °C. At this point the FSB signal THERMTRIP# will go active. THERMTRIP#
activation is independent of processor activity and does not generate any bus cycles. When
THERMTRIP# is asserted, the processor core voltage must be shut down within the time specified
in Chapter 3.
§
Datasheet 83
Thermal Specifications and Design Considerations
84Datasheet
Loading...
+ hidden pages
You need points to download manuals.
1 point = 1 manual.
You can buy points or you can get point for every manual you upload.