Memory Management Unit (MMU)
Freescale Semiconductor
4-19
Version 4 ColdFire processor local buses use the same 2-cycle read pipeline developed for Version 3
ColdFire cores. Each processor local bus has 32-bit address and 32-bit read data paths. Version 4 ColdFire
cores use synchronous memory elements for all memory-control units. To support this, certain control
information and all address bits are sent on the processor local buses at the end of the cycle before the
initial bus access cycle (J cycle). The data processor local bus has an additional 32-bit write data path. For
processor-store operations, Version 4 ColdFire uses a late-write strategy, which can require two additional
data processor local bus cycles. This strategy yields the processor local bus pipeline behavior described in
.
The processor core contains two independent memory unit access controllers and two independent
processor local bus controllers. Each instruction and data processor local bus request is analyzed to see
which, if any, memory controller is referenced. This information, along with cache mode, store precision,
and fault information, is sourced during KC1.
The MMU is referenced concurrently with the memory unit access controllers. It has two independent
control sections to process simultaneously an instruction and data processor local bus request.
shows how the MMU and memory unit access controllers fit in the processor local bus pipeline. As the
diagram shows, core address and attributes access the mapping registers and the MMU. By the middle of
the KC1 cycle, the physical-memory address is available along with its corresponding access control.
shows more details of the MMU structure. At the beginning of the KC1 pipeline stage, the
TLB is accessed so the resulting physical address can be sourced to the cache controllers to factor into the
cache hit/miss determination. This is required because caches are virtually indexed but physically mapped.
KC2 stage
IC2
OC2
Operand-execute stage
n/a
EX
Late-write stage
n/a
DA
Table 4-13. Processor Local Bus Pipeline Cycles
Cycle
Description
J
Control and partial address broadcast (to start synchronous memories)
KC1
Complete address and control broadcast plus MMU information. During this cycle, all memory element
read operations are performed; memory arrays are accessed.
KC2
Select appropriate memory as source, return data to processor, handle cache misses or hold
processor local bus pipeline as needed.
EX
Optional write stage, pipeline address and control for store operations.
DA
Data available for stores from processor; memory element update occurs in the next cycle.
Table 4-12. Version 4 Processor Local Bus Memory Pipelines (continued)
Processor Local Bus Memory Pipeline Stage
Instruction Fetch Pipeline
Operand Execution Pipeline
Summary of Contents for MCF54455
Page 33: ...xxviii Freescale Semiconductor ...
Page 67: ...Freescale Semiconductor 1 ...
Page 125: ...Freescale Semiconductor 1 ...
Page 145: ...Enhanced Multiply Accumulate Unit EMAC 5 21 Freescale Semiconductor ...
Page 173: ...Cache 6 28 Freescale Semiconductor ...
Page 179: ...Static RAM SRAM 7 6 Freescale Semiconductor ...
Page 207: ...Power Management 9 16 Freescale Semiconductor ...
Page 323: ...Reset Controller Module 13 8 Freescale Semiconductor ...
Page 389: ...Pin Multiplexing and Control 16 44 Freescale Semiconductor ...
Page 575: ...PCI Bus Controller 22 58 Freescale Semiconductor ...
Page 600: ...Advanced Technology Attachment ATA Freescale Semiconductor 23 25 ...
Page 601: ...Freescale Semiconductor 1 ...
Page 842: ...I2 C Interface Freescale Semiconductor 33 16 ...
Page 843: ...Freescale Semiconductor 1 ...
Page 921: ...Revision History A 6 Freescale Semiconductor ...