Datasheet PIC16F8X: PIC16F83, PIC16F84, PIC16CR83, PIC16CR84 (Microchip) - 7

link to page 10
PIC16F8X 3.0 ARCHITECTURAL OVERVIEW
The high performance of the PIC16CXX family can be attributed to a number of architectural features commonly found in RISC microprocessors. To begin with, the PIC16CXX uses a Harvard architecture. This architecture has the program and data accessed from separate memories. So the device has a program memory bus and a data memory bus. This improves bandwidth over traditional von Neumann architecture where program and data are fetched from the same memory (accesses over the same bus). Separating program and data memory further allows instructions to be sized differently than the 8-bit wide data word. PIC16CXX opcodes are 14-bits wide, enabling single word instructions. The full 14-bit wide program memory bus fetches a 14-bit instruction in a single cycle. A two- stage pipeline overlaps fetch and execution of instruc- tions (Example 3-1). Consequently, all instructions exe- cute in a single cycle except for program branches. The PIC16F83 and PIC16CR83 address 512 x 14 of program memory, and the PIC16F84 and PIC16CR84 address 1K x 14 program memory. All program mem- ory is internal. The PIC16CXX can directly or indirectly address its register files or data memory. All special function registers including the program counter are mapped in the data memory. An orthogonal (symmetrical) instruction set makes it possible to carry out any oper- ation on any register using any addressing mode. This symmetrical nature and lack of ‘special optimal situations’ make programming with the PIC16CXX simple yet efficient. In addition, the learning curve is reduced significantly.  1996-2013 Microchip Technology Inc. DS30430D-page 7