User manual

Table Of Contents
Zynq-7000 AP SoC Technical Reference Manual www.xilinx.com 89
UG585 (v1.11) September 27, 2016
Chapter 3: Application Processing Unit
Debug and Trace Interfaces
Each Cortex-A9 processor has a standard 32-bit APB slave port that operates at the CPU_1x clock
frequency and is accessed through the debug APB bus master in the SOC debug block. The operation
of this block is explained in the corresponding chapter of this document.
The Cortex-A9 processors also include a pair of interfaces for trace generation and cross trigger
control. The trace source interface from each core is a 32-bit CoreSight standard ATB master port
that operates at the speed of the PS interconnect (CPU_2x clock), and is connected to the funnel in
the SOC debug block. Each core also has a 4-bit standard CoreSight cross trigger interface that
operates at the interconnect frequency (CPU_2x clock) and is connected to the cross trigger matrix
(CTM) in the SOC debug block.
Other Interfaces
Each Cortex-A9 processor has multiple control bits that are driven through the System-Level Control
register (SLCR). This includes a 4-bit interface that drives the CoreSight standard security signals and
also static configuration signals for controlling CP15 and SW programmability.
There are also other interfaces including the event and interrupt interfaces that are explained later in
this chapter.
3.2.7 NEON
The Cortex-A9 NEON MPE extends the Cortex-A9 functionality to provide support for the ARM
v7 advanced SIMD and vector floating-point v3 (VFPv3) instruction sets. The Cortex-A9 NEON
MPE supports all addressing modes and data processing operations described in the ARM
Architecture Reference Manual.
The Cortex-A9 NEON MPE features are:
SIMD vector and scalar single-precision floating-point computation
°
Unsigned and signed integers
°
Single bit coefficient polynomials
°
Single-precision floating-point values
The operations supported by the NEON co-processor include:
°
Addition and subtraction
°
Multiplication with optional accumulation
°
Maximum or minimum value driven lane selection operations
°
Inverse square-root approximation
°
Comprehensive data-structure load instructions, including register-bank-resident table
lookup.
Scalar double-precision floating-point computation
SIMD and scalar half-precision floating-point conversion
8, 16, 32, and 64-bit signed and unsigned integer SIMD computation