floating point - Why does using float instead of double not improve Android performance? -

-

since smart phones (at least ones, can find specs on) have 32-bit processors, imagine using single precision floating-point values in extensive calculations perform better doubles. however, doesn't seem case.

even if avoid type casts, , use floatmath package whenever possible, can hardly see improvements in performance except memory use, when comparing float-based methods double-based ones.

i working on rather large, calculation intensive sound analysis tool, doing several million multiplications , additions per second. since double precision multiplication on 32-bit processor takes several clock cycles vs. 1 single precision, assuming type change noticeable... isn't :-(

is there explanation this? due way dalvik vm works, or what?

floating-point units on typical cpus perform of calculations in double-precision (or better) , round or convert whatever final precision is. in other words, 32-bit cpus have 64-bit fpus.

many phones have cpus include fpus, have fpus disabled save power, causing floating-point operations emulated (in case 32-bit floats advantage).

there vector units have 32-bit fpus, causing 64-bit floating-point operations take longer. simd units (like execute sse instructions) perform 32-bit , 64-bit operations in same amount of time, twice many 32-bit ops @ time, single 32-bit op won't go faster single 64-bit op.


Comments

Post a Comment

Popular posts from this blog

Javascript line number mapping -

-
magically formatted comments change reported line number of javascript errors in browsers; this: //@line n "f" n line number , f file name. unfortunately, //@line appears ungoogleable. know there documentation on feature, , browsers support it? (i found references here , here .) from can find available in mozilla based browsers. it using js_setoptions command can turn these options on or off depending on values passed. https://developer.mozilla.org/en/js_setoptions
Read more

c# - Is it possible to remove an existing registration from Autofac container builder? -

-
something along lines: builder.registertype<mytype>().as<itype>(); builder.registertype<mytype2>().as<itype>(); builder.deregistertype<mytype>().as<itype>() var container = builder.build(); var types = container.resolve<ienumerable<itype>>(); assert.istrue(types.count == 1); assert.istrue(types[0].gettype == typeof(mytype2)); scenario: go through bunch of assemblies , go register types want make sure have 1 implementation of given type. need before create container. track on own nice if autofac me bit. this cannot done directly using containerbuilder , unless start on new one. mind you, having first built container should able construct new container filtering away unwanted types , reusing registrations first container. this: ... var container = builder.build(); builder = new containerbuilder(); var components = container.componentregistry.registrations .where(cr => cr.activator.limittype != typ...
Read more

php - Mysql PK and FK char(36) vs int(10) -

-
i have read mysql can handle indexes , searches better if tables keys integers rather char(36) uuid's. is worth converting int(10)? note: use 1 server , have have plans use multiple databases concurrently therefore removing 1 of big reasons using uuid. our tables innodb if makes difference. thanks in advance. usually rdbms can handle integer keys pk more efficient, other datatypes. reason how build index column, yes: long dont require string (or other typed) keys, should use integers. however: char(36) , int(10) far away being equal, because int(10) much smaller, char(36). dont know, if require many different keys, should keep in mind. update, complete last paragraph: int(10) 32-bit, char(36) 36 - ^byte^ (= 288-bit). not mean, int consumes less space, means, char(36) has 4 times more different keys.
Read more