NVIDIA Performance Primitives (NPP)
Version 9.2
|
Modules | |
Basic NPP Data Types | |
Data Structures | |
struct | NppLibraryVersion |
struct | NppiPoint |
2D Point More... |
|
struct | NppPointPolar |
2D Polar Point More... |
|
struct | NppiSize |
2D Size This struct typically represents the size of a a rectangular region in two space. More... |
|
struct | NppiRect |
2D Rectangle This struct contains position and size information of a rectangle in two space. More... |
|
struct | NppiHOGConfig |
The NppiHOGConfig structure defines the configuration parameters for the HOG descriptor: More... |
|
struct | NppiHaarClassifier_32f |
struct | NppiHaarBuffer |
Macros | |
#define | NPP_MIN_8U ( 0 ) |
Minimum 8-bit unsigned integer. More... |
|
#define | NPP_MAX_8U ( 255 ) |
Maximum 8-bit unsigned integer. More... |
|
#define | NPP_MIN_16U ( 0 ) |
Minimum 16-bit unsigned integer. More... |
|
#define | NPP_MAX_16U ( 65535 ) |
Maximum 16-bit unsigned integer. More... |
|
#define | NPP_MIN_32U ( 0 ) |
Minimum 32-bit unsigned integer. More... |
|
#define | NPP_MAX_32U ( 4294967295U ) |
Maximum 32-bit unsigned integer. More... |
|
#define | NPP_MIN_64U ( 0 ) |
Minimum 64-bit unsigned integer. More... |
|
#define | NPP_MAX_64U ( 18446744073709551615ULL ) |
Maximum 64-bit unsigned integer. More... |
|
#define | NPP_MIN_8S (-127 - 1 ) |
Minimum 8-bit signed integer. More... |
|
#define | NPP_MAX_8S ( 127 ) |
Maximum 8-bit signed integer. More... |
|
#define | NPP_MIN_16S (-32767 - 1 ) |
Minimum 16-bit signed integer. More... |
|
#define | NPP_MAX_16S ( 32767 ) |
Maximum 16-bit signed integer. More... |
|
#define | NPP_MIN_32S (-2147483647 - 1 ) |
Minimum 32-bit signed integer. More... |
|
#define | NPP_MAX_32S ( 2147483647 ) |
Maximum 32-bit signed integer. More... |
|
#define | NPP_MAX_64S ( 9223372036854775807LL ) |
Maximum 64-bit signed integer. More... |
|
#define | NPP_MIN_64S (-9223372036854775807LL - 1) |
Minimum 64-bit signed integer. More... |
|
#define | NPP_MINABS_32F ( 1.175494351e-38f ) |
Smallest positive 32-bit floating point value. More... |
|
#define | NPP_MAXABS_32F ( 3.402823466e+38f ) |
Largest positive 32-bit floating point value. More... |
|
#define | NPP_MINABS_64F ( 2.2250738585072014e-308 ) |
Smallest positive 64-bit floating point value. More... |
|
#define | NPP_MAXABS_64F ( 1.7976931348623158e+308 ) |
Largest positive 64-bit floating point value. More... |
|
#define | NPP_HOG_MAX_CELL_SIZE (16) |
max horizontal/vertical pixel size of cell. More... |
|
#define | NPP_HOG_MAX_BLOCK_SIZE (64) |
max horizontal/vertical pixel size of block. More... |
|
#define | NPP_HOG_MAX_BINS_PER_CELL (16) |
max number of histogram bins. More... |
|
#define | NPP_HOG_MAX_CELLS_PER_DESCRIPTOR (256) |
max number of cells in a descriptor window. More... |
|
#define | NPP_HOG_MAX_OVERLAPPING_BLOCKS_PER_DESCRIPTOR (256) |
max number of overlapping blocks in a descriptor window. More... |
|
#define | NPP_HOG_MAX_DESCRIPTOR_LOCATIONS_PER_CALL (128) |
max number of descriptor window locations per function call. More... |
|
#define NPP_HOG_MAX_BINS_PER_CELL (16) |
max number of histogram bins.
#define NPP_HOG_MAX_BLOCK_SIZE (64) |
max horizontal/vertical pixel size of block.
#define NPP_HOG_MAX_CELL_SIZE (16) |
max horizontal/vertical pixel size of cell.
#define NPP_HOG_MAX_CELLS_PER_DESCRIPTOR (256) |
max number of cells in a descriptor window.
#define NPP_HOG_MAX_DESCRIPTOR_LOCATIONS_PER_CALL (128) |
max number of descriptor window locations per function call.
#define NPP_HOG_MAX_OVERLAPPING_BLOCKS_PER_DESCRIPTOR (256) |
max number of overlapping blocks in a descriptor window.
#define NPP_MAX_16S ( 32767 ) |
Maximum 16-bit signed integer.
#define NPP_MAX_16U ( 65535 ) |
Maximum 16-bit unsigned integer.
#define NPP_MAX_32S ( 2147483647 ) |
Maximum 32-bit signed integer.
#define NPP_MAX_32U ( 4294967295U ) |
Maximum 32-bit unsigned integer.
#define NPP_MAX_64S ( 9223372036854775807LL ) |
Maximum 64-bit signed integer.
#define NPP_MAX_64U ( 18446744073709551615ULL ) |
Maximum 64-bit unsigned integer.
#define NPP_MAX_8S ( 127 ) |
Maximum 8-bit signed integer.
#define NPP_MAX_8U ( 255 ) |
Maximum 8-bit unsigned integer.
#define NPP_MAXABS_32F ( 3.402823466e+38f ) |
Largest positive 32-bit floating point value.
#define NPP_MAXABS_64F ( 1.7976931348623158e+308 ) |
Largest positive 64-bit floating point value.
#define NPP_MIN_16S (-32767 - 1 ) |
Minimum 16-bit signed integer.
#define NPP_MIN_16U ( 0 ) |
Minimum 16-bit unsigned integer.
#define NPP_MIN_32S (-2147483647 - 1 ) |
Minimum 32-bit signed integer.
#define NPP_MIN_32U ( 0 ) |
Minimum 32-bit unsigned integer.
#define NPP_MIN_64S (-9223372036854775807LL - 1) |
Minimum 64-bit signed integer.
#define NPP_MIN_64U ( 0 ) |
Minimum 64-bit unsigned integer.
#define NPP_MIN_8S (-127 - 1 ) |
Minimum 8-bit signed integer.
#define NPP_MIN_8U ( 0 ) |
Minimum 8-bit unsigned integer.
#define NPP_MINABS_32F ( 1.175494351e-38f ) |
Smallest positive 32-bit floating point value.
#define NPP_MINABS_64F ( 2.2250738585072014e-308 ) |
Smallest positive 64-bit floating point value.
enum NppCmpOp |
enum NppHintAlgorithm |
enum NppiAlphaOp |
enum NppiAxis |
enum NppiBorderType |
enum NppiHuffmanTableType |
Filtering methods.
enum NppiMaskSize |
enum NppiNorm |
enum NppRoundMode |
Rounding Modes.
The enumerated rounding modes are used by a large number of NPP primitives to allow the user to specify the method by which fractional values are converted to integer values. Also see Rounding Modes.
For NPP release 5.5 new names for the three rounding modes are introduced that are based on the naming conventions for rounding modes set forth in the IEEE-754 floating-point standard. Developers are encouraged to use the new, longer names to be future proof as the legacy names will be deprecated in subsequent NPP releases.
Enumerator | |
---|---|
NPP_RND_NEAR |
Round to the nearest even integer. All fractional numbers are rounded to their nearest integer. The ambiguous cases (i.e. <integer>.5) are rounded to the closest even integer. E.g.
|
NPP_ROUND_NEAREST_TIES_TO_EVEN |
Alias name for NPP_RND_NEAR. |
NPP_RND_FINANCIAL |
Round according to financial rule. All fractional numbers are rounded to their nearest integer. The ambiguous cases (i.e. <integer>.5) are rounded away from zero. E.g.
|
NPP_ROUND_NEAREST_TIES_AWAY_FROM_ZERO |
Alias name for NPP_RND_FINANCIAL. |
NPP_RND_ZERO |
Round towards zero (truncation). All fractional numbers of the form <integer>.<decimals> are truncated to <integer>.
|
NPP_ROUND_TOWARD_ZERO |
Alias name for NPP_RND_ZERO. |
enum NppStatus |
Error Status Codes.
Almost all NPP function return error-status information using these return codes. Negative return codes indicate errors, positive return codes indicate warnings, a return code of 0 indicates success.
enum NppsZCType |