Floating-point operations

 

libsimdpp

Types

Capabilities

Operations

Conversions

Bitwise operations

Floating-point operations

Integer operations

Memory access operations

Shuffle operations

Miscellaneous operations

 

Floating-point operations

Elementary operations
add sub	mul div	fmadd fmsub	neg
Rounding
round ceil	floor trunc
Comparisons
cmp_eq cmp_neq	cmp_lt cmp_le	cmp_gt cmp_ge
Reduction
reduce_add reduce_min	reduce_mul reduce_max
Miscellaneous
abs sign	min max	isnan isnan2
Square root and reciprocal
sqrt	rcp_e rcp_rh	rsqrt_e rsqrt_rh

 

The following simple operations for floating-point computations are provided.

Elementary operations
add	performs addition (function template)
sub	performs subtraction (function template)
mul	performs multiplication (function template)
fmadd	performs fused multiply-add (function template)
fmsub	performs fused multiply-subtract (function template)
div	performs division (function template)
Rounding
round	rounds values towards nearest integer (function template)
ceil	rounds values towards positive infinity (function template)
floor	rounds values towards negative infinity (function template)
trunc	rounds values towards zero (function template)
Comparisons
cmp_eq	compares vector elements for equality (function template)
cmp_neq	compares vector elements for inequality (function template)
cmp_lt	compares vector elements for less than (function template)
cmp_le	compares vector elements for less than or equal (function template)
cmp_gt	compares vector elements for greater than (function template)
cmp_ge	compares vector elements for greater than or equal (function template)
Miscellaneous
abs	computes absolute value (function template)
sign	extracts sign bit (function template)
min	selects minimum values (function template)
max	selects maximum values (function template)
isnan	checks if elements are NaN (function template)
isnan2	checks if elements in two vectors are NaN (function template)
Square root and reciprocal
sqrt	computes square root (function template)
rcp_e	estimates reciprocal (function template)
rcp_rh	performs a single Newton-Rhapson iteration improving reciprocal estimate (function template)
rsqrt_e	estimates reciprocal square root (function template)
rsqrt_rh	performs a single Newton-Rhapson iteration improving reciprocal square root estimate (function template)
Reduction
reduce_add	computes the sum of all elements in the vector (function template)
reduce_mul	computes the product of all elements in the vector (function template)
reduce_min	computes the minimum of all elements in the vector (function template)
reduce_max	computes the maximum of all elements in the vector (function template)