cosf approximations

contents

about

approximating cosine blog post (2015-04-21)

approximating cosine update blog post (2016-07-20)

approximations code git browse

"amalgam"

/proc/cpuinfo

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 9
model name	: Intel(R) Pentium(R) M processor 1500MHz
stepping	: 5
microcode	: 0x5
cpu MHz		: 1500.000
cache size	: 1024 KB
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 2
wp		: yes
flags		: fpu vme de pse tsc msr mce cx8 sep mtrr pge mca cmov clflush dts acpi mmx fxsr sse sse2 tm pbe bts est tm2
bogomips	: 2999.82
clflush size	: 64
cache_alignment	: 64
address sizes	: 32 bits physical, 32 bits virtual
power management:

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/i586-linux-gnu/4.9/lto-wrapper
Target: i586-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-i386 --with-arch-directory=i386 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-targets=all --enable-multiarch --with-arch-32=i586 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=i586-linux-gnu --host=i586-linux-gnu --target=i586-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "amalgam" quality

speed

cosf "amalgam" speed rnd large

cosf "amalgam" speed rnd small

cosf "amalgam" speed seq large

cosf "amalgam" speed seq small

"mocha"

/proc/cpuinfo

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 15
model		: 4
model name	: Intel(R) Pentium(R) 4 CPU 3.00GHz
stepping	: 3
microcode	: 0x5
cpu MHz		: 2992.564
cache size	: 2048 KB
physical id	: 0
siblings	: 2
core id		: 0
cpu cores	: 1
apicid		: 0
initial apicid	: 0
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm constant_tsc pebs bts pni dtes64 monitor ds_cpl est cid cx16 xtpr
bogomips	: 5985.12
clflush size	: 64
cache_alignment	: 128
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 15
model		: 4
model name	: Intel(R) Pentium(R) 4 CPU 3.00GHz
stepping	: 3
microcode	: 0x5
cpu MHz		: 2992.564
cache size	: 2048 KB
physical id	: 0
siblings	: 2
core id		: 0
cpu cores	: 1
apicid		: 1
initial apicid	: 1
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm constant_tsc pebs bts pni dtes64 monitor ds_cpl est cid cx16 xtpr
bogomips	: 5984.98
clflush size	: 64
cache_alignment	: 128
address sizes	: 36 bits physical, 48 bits virtual
power management:

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/i586-linux-gnu/4.9/lto-wrapper
Target: i586-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-i386 --with-arch-directory=i386 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-targets=all --enable-multiarch --with-arch-32=i586 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=i586-linux-gnu --host=i586-linux-gnu --target=i586-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "mocha" quality

speed

cosf "mocha" speed rnd large

cosf "mocha" speed rnd small

cosf "mocha" speed seq large

cosf "mocha" speed seq small

"espresso"

/proc/cpuinfo

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 13
model name	: Intel(R) Pentium(R) M processor 1.60GHz
stepping	: 6
microcode	: 0x17
cpu MHz		: 1600.000
cache size	: 2048 KB
fdiv_bug	: no
hlt_bug		: no
f00f_bug	: no
coma_bug	: no
fpu		: yes
fpu_exception	: yes
cpuid level	: 2
wp		: yes
flags		: fpu vme de pse tsc msr mce cx8 apic sep mtrr pge mca cmov clflush dts acpi mmx fxsr sse sse2 ss tm pbe bts est tm2
bogomips	: 3199.84
clflush size	: 64
cache_alignment	: 64
address sizes	: 32 bits physical, 32 bits virtual
power management:

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/i586-linux-gnu/4.9/lto-wrapper
Target: i586-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-i386 --with-arch-directory=i386 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-targets=all --enable-multiarch --with-arch-32=i586 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=i586-linux-gnu --host=i586-linux-gnu --target=i586-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "espresso" quality

speed

cosf "espresso" speed rnd large

cosf "espresso" speed rnd small

cosf "espresso" speed seq large

cosf "espresso" speed seq small

"latte"

/proc/cpuinfo

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 23
model name	: Intel(R) Core(TM)2 Duo CPU     P7550  @ 2.26GHz
stepping	: 10
microcode	: 0xa07
cpu MHz		: 2266.000
cache size	: 3072 KB
physical id	: 0
siblings	: 2
core id		: 0
cpu cores	: 2
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl aperfmperf pni dtes64 monitor ds_cpl est tm2 ssse3 cx16 xtpr pdcm sse4_1 xsave lahf_lm dtherm
bogomips	: 4522.80
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 6
model		: 23
model name	: Intel(R) Core(TM)2 Duo CPU     P7550  @ 2.26GHz
stepping	: 10
microcode	: 0xa07
cpu MHz		: 2266.000
cache size	: 3072 KB
physical id	: 0
siblings	: 2
core id		: 1
cpu cores	: 2
apicid		: 1
initial apicid	: 1
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl aperfmperf pni dtes64 monitor ds_cpl est tm2 ssse3 cx16 xtpr pdcm sse4_1 xsave lahf_lm dtherm
bogomips	: 4522.44
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/4.9/lto-wrapper
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-amd64 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --with-arch-32=i586 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "latte" quality

speed

cosf "latte" speed rnd large

cosf "latte" speed rnd small

cosf "latte" speed seq large

cosf "latte" speed seq small

"frappuccino"

/proc/cpuinfo

processor	: 0
vendor_id	: AuthenticAMD
cpu family	: 16
model		: 5
model name	: AMD Athlon(tm) II X4 640 Processor
stepping	: 3
microcode	: 0x10000b6
cpu MHz		: 3000.000
cache size	: 512 KB
physical id	: 0
siblings	: 4
core id		: 0
cpu cores	: 4
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good nopl nonstop_tsc extd_apicid pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt hw_pstate npt lbrv svm_lock nrip_save
bogomips	: 6026.76
TLB size	: 1024 4K pages
clflush size	: 64
cache_alignment	: 64
address sizes	: 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

processor	: 1
vendor_id	: AuthenticAMD
cpu family	: 16
model		: 5
model name	: AMD Athlon(tm) II X4 640 Processor
stepping	: 3
microcode	: 0x10000b6
cpu MHz		: 3000.000
cache size	: 512 KB
physical id	: 0
siblings	: 4
core id		: 1
cpu cores	: 4
apicid		: 1
initial apicid	: 1
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good nopl nonstop_tsc extd_apicid pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt hw_pstate npt lbrv svm_lock nrip_save
bogomips	: 6026.80
TLB size	: 1024 4K pages
clflush size	: 64
cache_alignment	: 64
address sizes	: 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

processor	: 2
vendor_id	: AuthenticAMD
cpu family	: 16
model		: 5
model name	: AMD Athlon(tm) II X4 640 Processor
stepping	: 3
microcode	: 0x10000b6
cpu MHz		: 3000.000
cache size	: 512 KB
physical id	: 0
siblings	: 4
core id		: 2
cpu cores	: 4
apicid		: 2
initial apicid	: 2
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good nopl nonstop_tsc extd_apicid pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt hw_pstate npt lbrv svm_lock nrip_save
bogomips	: 6026.82
TLB size	: 1024 4K pages
clflush size	: 64
cache_alignment	: 64
address sizes	: 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

processor	: 3
vendor_id	: AuthenticAMD
cpu family	: 16
model		: 5
model name	: AMD Athlon(tm) II X4 640 Processor
stepping	: 3
microcode	: 0x10000b6
cpu MHz		: 3000.000
cache size	: 512 KB
physical id	: 0
siblings	: 4
core id		: 3
cpu cores	: 4
apicid		: 3
initial apicid	: 3
fpu		: yes
fpu_exception	: yes
cpuid level	: 5
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good nopl nonstop_tsc extd_apicid pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt hw_pstate npt lbrv svm_lock nrip_save
bogomips	: 6026.84
TLB size	: 1024 4K pages
clflush size	: 64
cache_alignment	: 64
address sizes	: 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/4.9/lto-wrapper
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-amd64 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --with-arch-32=i586 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "frappuccino" quality

speed

cosf "frappuccino" speed rnd large

cosf "frappuccino" speed rnd small

cosf "frappuccino" speed seq large

cosf "frappuccino" speed seq small

"macchiato"

/proc/cpuinfo

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 23
model name      : Celeron(R) Dual-Core CPU       T3100  @ 1.90GHz
stepping        : 10
microcode       : 0xa07
cpu MHz         : 1895.244
cache size      : 1024 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl aperfmperf pni dtes64 monitor ds_cpl tm2 ssse3 cx16 xtpr pdcm xsave lahf_lm dtherm
bogomips        : 3790.48
clflush size    : 64
cache_alignment : 64
address sizes   : 36 bits physical, 48 bits virtual
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 23
model name      : Celeron(R) Dual-Core CPU       T3100  @ 1.90GHz
stepping        : 10
microcode       : 0xa07
cpu MHz         : 1895.244
cache size      : 1024 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl aperfmperf pni dtes64 monitor ds_cpl tm2 ssse3 cx16 xtpr pdcm xsave lahf_lm dtherm
bogomips        : 3790.48
clflush size    : 64
cache_alignment : 64
address sizes   : 36 bits physical, 48 bits virtual
power management:

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/4.9/lto-wrapper
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-amd64 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-amd64 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --with-arch-32=i586 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "macchiato" quality

speed

cosf "macchiato" speed rnd large

cosf "macchiato" speed rnd small

cosf "macchiato" speed seq large

cosf "macchiato" speed seq small

"americano"

/proc/cpuinfo

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 28
model name      : Intel(R) Atom(TM) CPU N455   @ 1.66GHz
stepping        : 10
cpu MHz         : 1666.000
cache size      : 512 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 1
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm constant_tsc arch_perfmon pebs bts aperfmperf pni dtes64 monitor ds_cpl est tm2 ssse3 cx16 xtpr pdcm movbe lahf_lm dtherm
bogomips        : 3324.92
clflush size    : 64
cache_alignment : 64
address sizes   : 32 bits physical, 48 bits virtual
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 28
model name      : Intel(R) Atom(TM) CPU N455   @ 1.66GHz
stepping        : 10
cpu MHz         : 1666.000
cache size      : 512 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 1
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm constant_tsc arch_perfmon pebs bts aperfmperf pni dtes64 monitor ds_cpl est tm2 ssse3 cx16 xtpr pdcm movbe lahf_lm dtherm
bogomips        : 3324.92
clflush size    : 64
cache_alignment : 64
address sizes   : 32 bits physical, 48 bits virtual
power management:

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/i586-linux-gnu/4.9/lto-wrapper
Target: i586-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Debian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-i386 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-i386 --with-arch-directory=i386 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-targets=all --enable-multiarch --with-arch-32=i586 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=i586-linux-gnu --host=i586-linux-gnu --target=i586-linux-gnu
Thread model: posix
gcc version 4.9.2 (Debian 4.9.2-10) 

quality

cosf "americano" quality

speed

cosf "americano" speed rnd large

cosf "americano" speed rnd small

cosf "americano" speed seq large

cosf "americano" speed seq small

"pi3b"

/proc/cpuinfo

processor       : 0
model name      : ARMv7 Processor rev 4 (v7l)
BogoMIPS        : 76.80
Features        : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm crc32 
CPU implementer : 0x41
CPU architecture: 7
CPU variant     : 0x0
CPU part        : 0xd03
CPU revision    : 4

processor       : 1
model name      : ARMv7 Processor rev 4 (v7l)
BogoMIPS        : 76.80
Features        : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm crc32 
CPU implementer : 0x41
CPU architecture: 7
CPU variant     : 0x0
CPU part        : 0xd03
CPU revision    : 4

processor       : 2
model name      : ARMv7 Processor rev 4 (v7l)
BogoMIPS        : 76.80
Features        : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm crc32 
CPU implementer : 0x41
CPU architecture: 7
CPU variant     : 0x0
CPU part        : 0xd03
CPU revision    : 4

processor       : 3
model name      : ARMv7 Processor rev 4 (v7l)
BogoMIPS        : 76.80
Features        : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm crc32 
CPU implementer : 0x41
CPU architecture: 7
CPU variant     : 0x0
CPU part        : 0xd03
CPU revision    : 4

Hardware        : BCM2709
Revision        : a22082
Serial          : 000000001b039344

gcc -v

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/arm-linux-gnueabihf/4.9/lto-wrapper
Target: arm-linux-gnueabihf
Configured with: ../src/configure -v --with-pkgversion='Raspbian 4.9.2-10' --with-bugurl=file:///usr/share/doc/gcc-4.9/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.9 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.9 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-libitm --disable-libquadmath --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.9-armhf/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.9-armhf --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.9-armhf --with-arch-directory=arm --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --disable-sjlj-exceptions --with-arch=armv6 --with-fpu=vfp --with-float=hard --enable-checking=release --build=arm-linux-gnueabihf --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf
Thread model: posix
gcc version 4.9.2 (Raspbian 4.9.2-10) 

quality

cosf "frappuccino" quality

speed

cosf "pi3b" speed rnd large

cosf "pi3b" speed rnd small

cosf "pi3b" speed seq large

cosf "pi3b" speed seq small

sonograms

spectrum of difference vs libm cosf() for a 5-second sweep from 20kHz to 20Hz at 48kHz sample rate

horizontal axis time 0 .. 5s, vertical axis frequency 240 .. 24000 Hz, black at -90dB, white at -150dB

generated with home-cooked code using fftw3

piecewise linear interpolation - 513×1 points - union{ double d; uint32_t i[2]; } range reduction
cosft
piecewise linear interpolation -  513×1 points - float to int cast and subtract range reduction
cosf1-09
piecewise linear interpolation - 1025×1 points - float to int cast and subtract range reduction
cosf1-10
piecewise linear interpolation - 2049×1 points - float to int cast and subtract range reduction
cosf1-11
piecewise linear interpolation - 4097×1 points - float to int cast and subtract range reduction
cosf1-12
piecewise linear interpolation - 8193×1 points - float to int cast and subtract range reduction
cosf1-13
piecewise linear interpolation -  512×2 points - float to int cast and subtract range reduction
cosf2-09
piecewise linear interpolation - 1024×2 points - float to int cast and subtract range reduction
cosf2-10
piecewise linear interpolation - 2048×2 points - float to int cast and subtract range reduction
cosf2-11
piecewise linear interpolation - 4096×2 points - float to int cast and subtract range reduction
cosf2-12
piecewise linear interpolation - 8192×2 points - float to int cast and subtract range reduction
cosf2-13
piecewise cubic interpolation -  16×4 points - float to int cast and subtract range reduction
cosf4-4
piecewise cubic interpolation -  32×4 points - float to int cast and subtract range reduction
cosf4-5
piecewise cubic interpolation -  64×4 points - float to int cast and subtract range reduction
cosf4-6
piecewise cubic interpolation - 128×4 points - float to int cast and subtract range reduction
cosf4-7
piecewise cubic interpolation - 256×4 points - float to int cast and subtract range reduction
cosf4-8
order 7 odd polynomial approximation - 4 constants - float to int cast and subtract range reduction
cosf7
order 9 odd polynomial approximation - 5 constants - float to int cast and subtract range reduction
cosf9

mathr.co.uk