
4-4
G2 PowerPC Core Reference Manual
For More Information On This Product,
Go to: www.freescale.com
MOTOROLA
Instruction Cache Organization and Control
Figure 4-1. Instruction Cache Organization
4.2.2
Instruction Cache Fill Operations
The G2 core instruction cache blocks are loaded in four 64-bit beats, with the
critical-double-word loaded first. The instruction cache allows sequential fetching during a
cache block load. On a cache miss, the critical and following double words read from
memory are simultaneously written to the instruction cache and forwarded to the dispatch
queue, thus minimizing stalls due to cache fill latency. There is no snooping of the
instruction cache. In the G2 core, the critical-double-word is simultaneously written to the
cache and forwarded to the requesting unit, thus minimizing stalls due to load delays.
4.2.3
Instruction Cache Control
In addition to instruction cache control instructions, the G2 core provides several HID0 bits
to control invalidating, disabling, and locking the instruction cache. The WIMG bits in the
page tables and the IBATs also affect the cacheability of pages and whether the pages are
considered guarded.
4.2.3.1
Instruction Cache Invalidation
Although the G2 core instruction cache is automatically invalidated during a power-on or
hard reset, asserting core_sreset does not invalidate the instruction cache. Software can
invalidate the contents of the instruction cache using the instruction cache flash invalidate
control bit, HID0[ICFI]. Flash invalidation of the instruction cache is accomplished by
setting ICFI bit (invalidates the cache) and subsequently clearing the ICFI bit (enables
normal operation) in two consecutive
mtspr
[HID0] instructions.
Address Tag 1
Address Tag 2
Address Tag 3
Block 1
Block 2
Block 3
128 Sets
Address Tag 0
Block 0
8 Words/Block
State
State
State
Words 0–7
Words 0–7
Words 0–7
Words 0–7
State
F
Freescale Semiconductor, Inc.
n
.