Module p

Source

Expand description

RISC-V Packed SIMD intrinsics; shared part.

RV64 only part is placed in riscv64 folder.

Functions§

add8Experimental: Adds packed 8-bit signed numbers, discarding overflow bits
add16Experimental: Adds packed 16-bit signed numbers, discarding overflow bits
clrs8Experimental: Count the number of redundant sign bits of the packed 8-bit elements
clrs16Experimental: Count the number of redundant sign bits of the packed 16-bit elements
clrs32Experimental: Count the number of redundant sign bits of the packed 32-bit elements
clz8Experimental: Count the number of leading zero bits of the packed 8-bit elements
clz16Experimental: Count the number of leading zero bits of the packed 16-bit elements
clz32Experimental: Count the number of leading zero bits of the packed 32-bit elements
cmpeq8Experimental: Compare equality for packed 8-bit elements
cmpeq16Experimental: Compare equality for packed 16-bit elements
cras16Experimental: Cross adds and subtracts packed 16-bit signed numbers, discarding overflow bits
crsa16Experimental: Cross subtracts and adds packed 16-bit signed numbers, discarding overflow bits
kabs8Experimental: Compute the absolute value of packed 8-bit signed integers
kabs16Experimental: Compute the absolute value of packed 16-bit signed integers
kadd8Experimental: Adds packed 8-bit signed numbers, saturating at the numeric bounds
kadd16Experimental: Adds packed 16-bit signed numbers, saturating at the numeric bounds
kaddhExperimental: Adds signed lower 16-bit content of two registers with Q15 saturation
kcras16Experimental: Cross adds and subtracts packed 16-bit signed numbers, saturating at the numeric bounds
kcrsa16Experimental: Cross subtracts and adds packed 16-bit signed numbers, saturating at the numeric bounds
ksll8Experimental: Logical left shift packed 8-bit elements, saturating at the numeric bounds
ksll16Experimental: Logical left shift packed 16-bit elements, saturating at the numeric bounds
kslra8Experimental: Logical saturating left then arithmetic right shift packed 8-bit elements
kslra8uExperimental: Logical saturating left then arithmetic right shift packed 8-bit elements
kslra16Experimental: Logical saturating left then arithmetic right shift packed 16-bit elements
kslra16uExperimental: Logical saturating left then arithmetic right shift packed 16-bit elements
kstas16Experimental: Straight adds and subtracts packed 16-bit signed numbers, saturating at the numeric bounds
kstsa16Experimental: Straight subtracts and adds packed 16-bit signed numbers, saturating at the numeric bounds
ksub8Experimental: Subtracts packed 8-bit signed numbers, saturating at the numeric bounds
ksub16Experimental: Subtracts packed 16-bit signed numbers, saturating at the numeric bounds
ksubhExperimental: Subtracts signed lower 16-bit content of two registers with Q15 saturation
pbsadExperimental: Calculate the sum of absolute difference of unsigned 8-bit data elements
pbsadaExperimental: Calculate and accumulate the sum of absolute difference of unsigned 8-bit data elements
pkbt16Experimental: Pack two 16-bit data from bottom and top half from 32-bit chunks
pktb16Experimental: Pack two 16-bit data from top and bottom half from 32-bit chunks
radd8Experimental: Halves the sum of packed 8-bit signed numbers, dropping least bits
radd16Experimental: Halves the sum of packed 16-bit signed numbers, dropping least bits
rcras16Experimental: Cross halves of adds and subtracts packed 16-bit signed numbers, dropping least bits
rcrsa16Experimental: Cross halves of subtracts and adds packed 16-bit signed numbers, dropping least bits
rstas16Experimental: Straight halves of adds and subtracts packed 16-bit signed numbers, dropping least bits
rstsa16Experimental: Straight halves of subtracts and adds packed 16-bit signed numbers, dropping least bits
rsub8Experimental: Halves the subtraction result of packed 8-bit signed numbers, dropping least bits
rsub16Experimental: Halves the subtraction result of packed 16-bit signed numbers, dropping least bits
scmple8Experimental: Compare whether 8-bit packed signed integers are less than or equal to the others
scmple16Experimental: Compare whether 16-bit packed signed integers are less than or equal to the others
scmplt8Experimental: Compare whether 8-bit packed signed integers are less than the others
scmplt16Experimental: Compare whether 16-bit packed signed integers are less than the others
sll8Experimental: Logical left shift packed 8-bit elements, discarding overflow bits
sll16Experimental: Logical left shift packed 16-bit elements, discarding overflow bits
smaqaExperimental: Multiply signed 8-bit elements and add 16-bit elements on results for packed 32-bit chunks
smaqasuExperimental: Multiply signed to unsigned 8-bit and add 16-bit elements on results for packed 32-bit chunks
smax8Experimental: Get maximum values from 8-bit packed signed integers
smax16Experimental: Get maximum values from 16-bit packed signed integers
smin8Experimental: Get minimum values from 8-bit packed signed integers
smin16Experimental: Get minimum values from 16-bit packed signed integers
sra8Experimental: Arithmetic right shift packed 8-bit elements without rounding up
sra8uExperimental: Arithmetic right shift packed 8-bit elements with rounding up
sra16Experimental: Arithmetic right shift packed 16-bit elements without rounding up
sra16uExperimental: Arithmetic right shift packed 16-bit elements with rounding up
srl8Experimental: Logical right shift packed 8-bit elements without rounding up
srl8uExperimental: Logical right shift packed 8-bit elements with rounding up
srl16Experimental: Logical right shift packed 16-bit elements without rounding up
srl16uExperimental: Logical right shift packed 16-bit elements with rounding up
stas16Experimental: Straight adds and subtracts packed 16-bit signed numbers, discarding overflow bits
stsa16Experimental: Straight subtracts and adds packed 16-bit signed numbers, discarding overflow bits
sub8Experimental: Subtracts packed 8-bit signed numbers, discarding overflow bits
sub16Experimental: Subtracts packed 16-bit signed numbers, discarding overflow bits
sunpkd810Experimental: Unpack first and zeroth into two 16-bit signed halfwords in each 32-bit chunk
sunpkd820Experimental: Unpack second and zeroth into two 16-bit signed halfwords in each 32-bit chunk
sunpkd830Experimental: Unpack third and zeroth into two 16-bit signed halfwords in each 32-bit chunk
sunpkd831Experimental: Unpack third and first into two 16-bit signed halfwords in each 32-bit chunk
sunpkd832Experimental: Unpack third and second into two 16-bit signed halfwords in each 32-bit chunk
swap8Experimental: Swap the 8-bit bytes within each 16-bit halfword of a register.
swap16Experimental: Swap the 16-bit halfwords within each 32-bit word of a register
ucmple8Experimental: Compare whether 8-bit packed unsigned integers are less than or equal to the others
ucmple16Experimental: Compare whether 16-bit packed unsigned integers are less than or equal to the others
ucmplt8Experimental: Compare whether 8-bit packed unsigned integers are less than the others
ucmplt16Experimental: Compare whether 16-bit packed unsigned integers are less than the others
ukadd8Experimental: Adds packed 8-bit unsigned numbers, saturating at the numeric bounds
ukadd16Experimental: Adds packed 16-bit unsigned numbers, saturating at the numeric bounds
ukaddhExperimental: Adds signed lower 16-bit content of two registers with U16 saturation
ukcras16Experimental: Cross adds and subtracts packed 16-bit unsigned numbers, saturating at the numeric bounds
ukcrsa16Experimental: Cross subtracts and adds packed 16-bit unsigned numbers, saturating at the numeric bounds
ukstas16Experimental: Straight adds and subtracts packed 16-bit unsigned numbers, saturating at the numeric bounds
ukstsa16Experimental: Straight subtracts and adds packed 16-bit unsigned numbers, saturating at the numeric bounds
uksub8Experimental: Subtracts packed 8-bit unsigned numbers, saturating at the numeric bounds
uksub16Experimental: Subtracts packed 16-bit unsigned numbers, saturating at the numeric bounds
uksubhExperimental: Subtracts signed lower 16-bit content of two registers with U16 saturation
umaqaExperimental: Multiply unsigned 8-bit elements and add 16-bit elements on results for packed 32-bit chunks
umax8Experimental: Get maximum values from 8-bit packed unsigned integers
umax16Experimental: Get maximum values from 16-bit packed unsigned integers
umin8Experimental: Get minimum values from 8-bit packed unsigned integers
umin16Experimental: Get minimum values from 16-bit packed unsigned integers
uradd8Experimental: Halves the sum of packed 8-bit unsigned numbers, dropping least bits
uradd16Experimental: Halves the sum of packed 16-bit unsigned numbers, dropping least bits
urcras16Experimental: Cross halves of adds and subtracts packed 16-bit unsigned numbers, dropping least bits
urcrsa16Experimental: Cross halves of subtracts and adds packed 16-bit unsigned numbers, dropping least bits
urstas16Experimental: Straight halves of adds and subtracts packed 16-bit unsigned numbers, dropping least bits
urstsa16Experimental: Straight halves of subtracts and adds packed 16-bit unsigned numbers, dropping least bits
ursub8Experimental: Halves the subtraction result of packed 8-bit unsigned numbers, dropping least bits
ursub16Experimental: Halves the subtraction result of packed 16-bit unsigned numbers, dropping least bits
zunpkd810Experimental: Unpack first and zeroth into two 16-bit unsigned halfwords in each 32-bit chunk
zunpkd820Experimental: Unpack second and zeroth into two 16-bit unsigned halfwords in each 32-bit chunk
zunpkd830Experimental: Unpack third and zeroth into two 16-bit unsigned halfwords in each 32-bit chunk
zunpkd831Experimental: Unpack third and first into two 16-bit unsigned halfwords in each 32-bit chunk
zunpkd832Experimental: Unpack third and second into two 16-bit unsigned halfwords in each 32-bit chunk

Module pCopy item path

Functions§

Module p