help!my machine reboot very often!

here is the crash dump file!
1:
Microsoft (R) Windows Debugger Version 6.5.0003.7
Copyright (c) Microsoft Corporation. All rights reserved.


Loading Dump File [D:\Documents and Settings\Linsion\桌面\Minidump\Mini071306-07.dmp]
Mini Kernel Dump File: Only registers and stack trace are available

Symbol search path is: C:\windows\Symbol
Executable search path is:
Unable to load image ntoskrnl.exe, Win32 error 2
*** WARNING: Unable to verify timestamp for ntoskrnl.exe
Windows XP Kernel Version 2600 (Service Pack 2) UP Free x86 compatible
Product: WinNt, suite: TerminalServer SingleUserTS
Kernel base = 0x804e0000 PsLoadedModuleList = 0x80563420
Debug session time: Thu Jul 13 19:39:43.640 2006 (GMT+8)
System Uptime: 0 days 1:23:45.250
Unable to load image ntoskrnl.exe, Win32 error 2
*** WARNING: Unable to verify timestamp for ntoskrnl.exe
Loading Kernel Symbols
................................................................................................................
Loading unloaded module list
...........
Loading User Symbols
*******************************************************************************
* *
* Bugcheck Analysis *
* *
*******************************************************************************

Use !analyze -v to get detailed debugging information.

BugCheck 1000000A, {fa0c2d44, 2, 1, 804e2136}

Probably caused by : ntoskrnl.exe ( nt!KiXMMIZeroPage+9d )

Followup: MachineOwner
---------

kd> !analyze -v
*******************************************************************************
* *
* Bugcheck Analysis *
* *
*******************************************************************************

IRQL_NOT_LESS_OR_EQUAL (a)
An attempt was made to access a pageable (or completely invalid) address at an
interrupt request level (IRQL) that is too high. This is usually
caused by drivers using improper addresses.
If a kernel debugger is available get the stack backtrace.
Arguments:
Arg1: fa0c2d44, memory referenced
Arg2: 00000002, IRQL
Arg3: 00000001, value 0 = read operation, 1 = write operation
Arg4: 804e2136, address which referenced memory

Debugging Details:
------------------


WRITE_ADDRESS: fa0c2d44

CURRENT_IRQL: 2

FAULTING_IP:
nt!KiXMMIZeroPage+9d
804e2136 8902 mov [edx],eax

CUSTOMER_CRASH_COUNT: 7

DEFAULT_BUCKET_ID: COMMON_SYSTEM_FAULT

BUGCHECK_STR: 0xA

LAST_CONTROL_TRANSFER: from 00000000 to 804e2136

STACK_TEXT:
f8950dfc 00000000 f8209dba 81e6c0d8 81eeb008 nt!KiXMMIZeroPage+0x9d


FOLLOWUP_IP:
nt!KiXMMIZeroPage+9d
804e2136 8902 mov [edx],eax

SYMBOL_STACK_INDEX: 0

FOLLOWUP_NAME: MachineOwner

SYMBOL_NAME: nt!KiXMMIZeroPage+9d

MODULE_NAME: nt

IMAGE_NAME: ntoskrnl.exe

DEBUG_FLR_IMAGE_TIMESTAMP: 42250ff9

STACK_COMMAND: kb

FAILURE_BUCKET_ID: 0xA_W_nt!KiXMMIZeroPage+9d

BUCKET_ID: 0xA_W_nt!KiXMMIZeroPage+9d

Followup: MachineOwner
---------

 

another crash dump file:




*** WARNING: Unable to verify timestamp for nv4_mini.sys
Probably caused by : nv4_mini.sys ( nv4_mini!notifyBufferHWComplete+1317 )

Followup: MachineOwner
---------

kd> !analyze -v
*******************************************************************************
* *
* Bugcheck Analysis *
* *
*******************************************************************************

IRQL_NOT_LESS_OR_EQUAL (a)
An attempt was made to access a pageable (or completely invalid) address at an
interrupt request level (IRQL) that is too high. This is usually
caused by drivers using improper addresses.
If a kernel debugger is available get the stack backtrace.
Arguments:
Arg1: 031c2d44, memory referenced
Arg2: 00000002, IRQL
Arg3: 00000000, value 0 = read operation, 1 = write operation
Arg4: 804e20aa, address which referenced memory

Debugging Details:
------------------


READ_ADDRESS: 031c2d44

CURRENT_IRQL: 2

FAULTING_IP:
nt!KiXMMIZeroPage+11
804e20aa 8b02 mov eax,[edx]

CUSTOMER_CRASH_COUNT: 6

DEFAULT_BUCKET_ID: COMMON_SYSTEM_FAULT

BUGCHECK_STR: 0xA

LAST_CONTROL_TRANSFER: from 81c522b4 to 804e20aa

STACK_TEXT:
f8950e0c 81c522b4 81d44008 f8209df7 81d48ab8 nt!KiXMMIZeroPage+0x11
WARNING: Frame IP not in any known module. Following frames may be wrong.
f8950e10 81d44008 f8209df7 81d48ab8 81d44008 0x81c522b4
f8950e14 f8209df7 81d48ab8 81d44008 0bb14d44 0x81d44008
f8950e18 81d48ab8 81d44008 0bb14d44 f8308b01 nv4_mini!notifyBufferHWComplete+0x1317
f8950e24 f8308b01 81d44008 0bb14d44 00000000 0x81d48ab8
f8950e48 00bb14d4 81ecae38 f830bfbd 81c82000 nv4_mini!nvHalGrLoadHW+0x161
00000000 00000000 00000000 00000000 00000000 0xbb14d4


FOLLOWUP_IP:
nv4_mini!notifyBufferHWComplete+1317
f8209df7 ?? ???

SYMBOL_STACK_INDEX: 3

FOLLOWUP_NAME: MachineOwner

SYMBOL_NAME: nv4_mini!notifyBufferHWComplete+1317

MODULE_NAME: nv4_mini

IMAGE_NAME: nv4_mini.sys

DEBUG_FLR_IMAGE_TIMESTAMP: 4074b958

STACK_COMMAND: kb

FAILURE_BUCKET_ID: 0xA_nv4_mini!notifyBufferHWComplete+1317

BUCKET_ID: 0xA_nv4_mini!notifyBufferHWComplete+1317

Followup: MachineOwner
---------