当前位置 & &
& ARM 64位处理器架构ARMv8技术浅析
ARM 64位处理器架构ARMv8技术浅析
17:24:41&&作者：
编辑：上方文Q &&)
让小伙伴们也看看：
阅读更多：
好文共享：
首页上一页
文章内容导航第1页 ARM 64位架构ARMv8浅析(一)
文章观点支持
当前平均分：0(0 次打分)
[04-03][04-02][04-01][03-31][03-31][03-30][03-30][03-29][03-28][03-26]
登录驱动之家
没有帐号？
用合作网站帐户直接登录11:22:151297
AArch64 Processor rev0360优化大师检测出来的s6cpu型号。请问这是7420处理器吗？
您需要注册登录后，才能回帖哦！
快速登录：AArch64 Options - Using the GNU Compiler Collection (GCC)
3.18.1 AArch64 Options
These options are defined for AArch64 implementations:
-mabi=nameGenerate code for the specified data model.
Permissible values
are &ilp32& for SysV-like data model where int, long int and pointers
are 32 bits, and &lp64& for SysV-like data model where int is 32 bits,
but long int and pointers are 64 bits.
The default depends on the specific target configuration.
the LP64 and ILP32 ABIs are not link- you must compile your
entire program with the same ABI, and link with a compatible set of libraries.
-mbig-endianGenerate big-endian code.
This is the default when GCC is configured for an
&aarch64_be-*-*& target.
-mgeneral-regs-onlyGenerate code which uses only the general-purpose registers.
This will prevent
the compiler from using floating-point and Advanced SIMD registers but will not
impose any restrictions on the assembler.
-mlittle-endianGenerate little-endian code.
This is the default when GCC is configured for an
&aarch64-*-*& but not an &aarch64_be-*-*& target.
-mcmodel=tinyGenerate code for the tiny code model.
The program and its statically defined
symbols must be within 1MB of each other.
Programs can be statically or
dynamically linked.
-mcmodel=smallGenerate code for the small code model.
The program and its statically defined
symbols must be within 4GB of each other.
Programs can be statically or
dynamically linked.
This is the default code model.
-mcmodel=largeGenerate code for the large code model.
This makes no assumptions about
addresses and sizes of sections.
Programs can be statically linked only.
-mstrict-alignAvoid generating memory accesses that may not be aligned on a natural object
boundary as described in the architecture specification.
-momit-leaf-frame-pointer-mno-omit-leaf-frame-pointerOmit or keep the frame pointer in leaf functions.
The former behavior is the
-mtls-dialect=descUse TLS descriptors as the thread-local storage mechanism for dynamic accesses
of TLS variables.
This is the default.
-mtls-dialect=traditionalUse traditional TLS as the thread-local storage mechanism for dynamic accesses
of TLS variables.
-mtls-size=sizeSpecify bit size of immediate TLS offsets.
Valid values are 12, 24, 32, 48.
This option requires binutils 2.26 or newer.
-mfix-cortex-a53-835769-mno-fix-cortex-a53-835769Enable or disable the workaround for the ARM Cortex-A53 erratum number 835769.
This involves inserting a NOP instruction between memory instructions and
64-bit integer multiply-accumulate instructions.
-mfix-cortex-a53-843419-mno-fix-cortex-a53-843419Enable or disable the workaround for the ARM Cortex-A53 erratum number 843419.
This erratum workaround is made at link time and this will only pass the
corresponding flag to the linker.
-mlow-precision-recip-sqrt-mno-low-precision-recip-sqrtEnable or disable reciprocal square root approximation.
This option only has an effect if -ffast-math or
-funsafe-math-optimizations is used as well.
Enabling this reduces
precision of reciprocal square root results to about 16 bits for
single precision and to 32 bits for double precision.
-march=nameSpecify the name of the target architecture and, optionally, one or
more feature modifiers.
This option has the form
-march=arch{+[no]feature}*.
The permissible values for arch are &armv8-a&,
&armv8.1-a& or native.
The value &armv8.1-a& implies &armv8-a& and enables compiler
support for the ARMv8.1 architecture extension.
In particular, it
enables the &+crc& and &+lse& features.
The value &native& is available on native AArch64 GNU/Linux and
causes the compiler to pick the architecture of the host system.
option has no effect if the compiler is unable to recognize the
architecture of the host system,
The permissible values for feature are listed in the sub-section
Where conflicting feature modifiers are
specified, the right-most feature is used.
GCC uses name to determine what kind of instructions it can emit
when generating assembly code.
If -march is specified
without either of -mtune or -mcpu also being
specified, the code is tuned to perform well across a range of target
processors implementing the target architecture.
-mtune=nameSpecify the name of the target processor for which GCC should tune the
performance of the code.
Permissible values for this option are:
&generic&, &cortex-a35&, &cortex-a53&, &cortex-a57&,
&cortex-a72&, &exynos-m1&, &qdf24xx&, &thunderx&,
&xgene1&, &cortex-a57.cortex-a53&, &cortex-a72.cortex-a53&,
The values &cortex-a57.cortex-a53&, &cortex-a72.cortex-a53&
specify that GCC should tune for a big.LITTLE system.
Additionally on native AArch64 GNU/Linux systems the value
&native& tunes performance to the host system.
This option has no effect
if the compiler is unable to recognize the processor of the host system.
Where none of -mtune=, -mcpu= or -march=
are specified, the code is tuned to perform well across a range
of target processors.
This option cannot be suffixed by feature modifiers.
-mcpu=nameSpecify the name of the target processor, optionally suffixed by one
or more feature modifiers.
This option has the form
-mcpu=cpu{+[no]feature}*, where
the permissible values for cpu are the same as those available
for -mtune.
The permissible values for feature are
documented in the sub-section on
Where conflicting feature modifiers are
specified, the right-most feature is used.
GCC uses name to determine what kind of instructions it can emit when
generating assembly code (as if by -march) and to determine
the target processor for which to tune for performance (as if
by -mtune).
Where this option is used in conjunction
with -march or -mtune, those options take precedence
over the appropriate part of this option.
-moverride=stringOverride tuning decisions made by the back-end in response to a
-mtune= switch.
The syntax, semantics, and accepted values
for string in this option are not guaranteed to be consistent
across releases.
This option is only intended to be useful when developing GCC.
-mpc-relative-literal-loadsEnable PC-relative literal loads.
With this option literal pools are
accessed using a single instruction and emitted after each function.
limits the maximum size of functions to 1MB.
This is enabled by default for
-mcmodel=tiny.
3.18.1.1 -march and -mcpu Feature Modifiers
Feature modifiers used with -march and -mcpu can be any of
the following and their inverses nofeature:
&crc&Enable CRC extension.
This is on by default for
-march=armv8.1-a.
&crypto&Enable Crypto extension.
This also enables Advanced SIMD and floating-point
instructions.
&fp&Enable floating-point instructions.
This is on by default for all possible
values for options -march and -mcpu.
&simd&Enable Advanced SIMD instructions.
This also enables floating-point
instructions.
This is on by default for all possible values for options
-march and -mcpu.
&lse&Enable Large System Extension instructions.
This is on by default for
-march=armv8.1-a.
Feature crypto implies simd, which implies fp.
Conversely, nofp implies nosimd, which implies<div id="click_content_aid_
<div id="favrite_content_aid_
苹果A7处理器：不止64位这么简单
苹果A7处理器：不止64位这么简单
16:35&&|&&作者：
&&|&&关键字：,,,,,
A7处理器CPU：AArch64先锋
　　如果没有世界末日般的意外，A7也会是ARM指令集兼容的，而且是64位ARM指令集，属于ARMv8家族AArch64指令集（简称A64），目前的ARM都是32位AArch32位指令集（简称A32）。本文并不打算详细介绍A64指令集相比A32指令集改进了什么（简单了解的可以参考中文），我们逆向从苹果公布的描述来看A7与A64指令集有多少吻合的。
　　2倍的通用寄存器：A32有R0-R14总计15个通用寄存器，A64指令集有R0-R30总计31个通用寄存器，后者是前者的2倍，与苹果宣传的相符。
　　2倍的浮点寄存器：相对于通用寄存器的规模增加，A64的浮点寄存器变化其实不算大。A32有32个VFP标量浮点寄存器，每个都是64bit的，而且ARM的浮点寄存器使用使用的是小寄存器，好处是可以将两个小寄存器虚拟成位宽更大的寄存器，A32的32个VFP还可以当作16个128bit的浮点寄存器。
　　A64的浮点寄存器总数还是32个，不过每个的位宽提高到了128bit，算起来也可以说是原来的两倍，苹果所说的浮点寄存器提升跟A64指令集也是相符的。
　　A64的高级SIMD（ARM的NEON指令集）还支持DP双精度浮点运算，支持IEE
754这一主流CPU都支持的浮点运算标准等。除此之外，A64的指令集改进了内存指令，支持48bit物理内存寻址等等。
　　两相对比之下我们可以基本确认A7使用的正是ARMv8的A64指令集。
　　到此为此只算解决了第一步，使用64位ARM指令集并不代表一定会使用ARM推出的，后者包括Cortex-A57和Cortex-A53。苹果从A6开始走向了自行开发架构之路，不过我们也要看到，32位的A32指令集问世已有多年，而A64指令集推出才两三年的时间，而且此前尚未有真正产品问世，厂商对这个指令集掌握的还不是那么熟练，即便是高通苹果这样有技术的大公司，初涉A64指令集开发肯定也要参考ARM自家的Cortex-A50架构，这是一种比完全自行开发更稳妥的做法。正常的话，苹果应该会遵循这个思路来设计A7。
　　A57和A53的关系有点类似目前的A15和A7，数字大的是高性能、（相对的）大核心，数字小的是低功耗、低性能的小核心，苹果的A7应该会使用Cortex-A57等级的架构，因为高贵冷艳的苹果不可能选择低性能的A53架构。
　　支撑这个观点的其实不是苹果的气质问题，因为A53实在达不到苹果的性能水准。官方公布的资料中显示A7的CPU是初代iPhone的40倍，GPU是初代的56倍，直接对比A6的话差不多也是后者的两倍，。
A57相对A15性能提升明显，而A53相对A9性能提升就不明显
　　ARM官方公布的测试中，Cortex-A53在同样的1.2GHz频率下性能只比A9略高一点点，而A6正是基于A9架构的，所以A53这种低性能低功耗的架构不会是苹果的选择，A53还是交给ARM处理器的良心代表联发科/全志去搞这种人民群众喜闻乐见的低功耗小核心去吧。
不同ARM处理器的DMIPs/MHz性能
　　从每个内核的DMIP/MHz性能来看，A57少则4.1多则4.76，要比A9的2.5
DMIPS/MHz至少高出64%，别忘了A7处理器的频率还会提高，A6从之前的800MHz提高到了1.3GHz，A7据说达到了1.5GHz，毕竟使用了比A6更先进的28nm工艺。
　　再考虑到苹果不跟其他处理器厂商比CPU核心数的鸟性，A7依然会是双核设计，架构及频率上的双重优势积累下来，A7的CPU性能比A6提升一倍并不是难题。
　　从上面的猜测我们可以得出：苹果的A7是一款使用了ARMv8
AArch64指令集的64位处理器，很有可能以Cortex-A57架构为基础改进或者直接使用A57架构，其通用及浮点寄存器提高了一倍，性能比前代A6翻倍。再具体点的规格就是双核心1.5GHz频率，28nm HKMG工艺，但是这些还缺少佐证，等见过iPhone
5s真机再说。
1.3.2.A7处理器CPU：AArch64指令集先锋4.
本文读者还喜欢
容我吐槽一句
iPhone5的GPU规格比399七彩虹平板用的全志A31s还低。
一个是3核543，一个是三核544。
上次还被喷A31sGPU规格低。
（各种系统高贵冷艳优势摆一边只谈规格，联发科已经上最新的6系列，全志的规格也很高，完全是拳打脚踢高通狗的低端CPU）网友 [Guest] 的原贴：2楼最简单的，自己对比下两者游戏效果再来吐槽，你这智商都让人不忍吐槽，还学人说什么规格，规格就只有核心数和频率？你这一滴水也敢晃的纯洁真希望可以一直保持下去网友 [Guest] 的原贴：3楼这么破烂的CPU也好意思拿出来....64位又如何？？别人拿来跑圆周率，被红米爆....A7大概性能和 四核 1.0--1.1主频性能差不多，但是由于但核心的强势，在一些应用上比较出色，加上IOS系统的高度定制，具有一些超常发挥能力........就GPU部分来比较，是果子的弱势.....果子的配置，仅仅搭载的是 的分辨率，这种分辨率比一般的国产山寨手机的分辨率还不如.....如果以每一幅的像素填充来算。 仅仅只有72万多的像素填充工作量，而的主流1080P屏幕则已经达到了每一幅 207万以上的像素填充工作量，工作量是果子5S的接近3倍....你工作量只有别人的三分之一，能跑流畅游戏有什么好得意的？？就是尼采山寨手机，定制个640X400的屏幕，跑幅数都能秒飞你苹果5S....分辨率低下加上屏幕小，导致苹果手机的所谓流畅根本是掩耳盗铃。android有多少1080P的游戏？？？720P都没有普及完。手机游戏跟pc游戏一样，就算你有个4K屏幕，游戏分辨率跳到720P，渣渣硬件也能玩。
逗比。智商堪忧。
（你可匿名或登录后发表评论。没有帐号可，或使用和直接登录）
非著名编辑，自认为是个理性、有内涵的观察者，实则腹黑、心不黑，坚信阳光普照大地，只待涤荡眼前的黑暗。
扫一扫右边的二维码
关注超能网微信账号
主板、显卡满减特价
六一儿童节买买买
Intel 400G PCIe SSD特价1879元
辣么大的屏手机导购