Class X86.Sse4_1
Syntax
public static class Sse4_1
Properties
IsSse41Supported
Evaluates to true at compile time if SSE 4.1 intrinsics are supported.
Declaration
public static bool IsSse41Supported { get; }
Property Value
Methods
blend_epi16(v128, v128, Int32)
Blend packed 16-bit integers from "a" and "b" using control mask "imm8", and store the results in "dst".
Declaration
public static v128 blend_epi16(v128 a, v128 b, int imm8)
Parameters
Returns
blend_pd(v128, v128, Int32)
Blend packed double-precision (64-bit) floating-point elements from "a" and "b" using control mask "imm8", and store the results in "dst".
Declaration
public static v128 blend_pd(v128 a, v128 b, int imm8)
Parameters
Returns
blend_ps(v128, v128, Int32)
Blend packed single-precision (32-bit) floating-point elements from "a" and "b" using control mask "imm8", and store the results in "dst".
Declaration
public static v128 blend_ps(v128 a, v128 b, int imm8)
Parameters
Returns
blendv_epi8(v128, v128, v128)
Blend packed 8-bit integers from "a" and "b" using "mask", and store the results in "dst".
Declaration
public static v128 blendv_epi8(v128 a, v128 b, v128 mask)
Parameters
Returns
blendv_pd(v128, v128, v128)
Blend packed double-precision (64-bit) floating-point elements from "a" and "b" using "mask", and store the results in "dst".
Declaration
public static v128 blendv_pd(v128 a, v128 b, v128 mask)
Parameters
Returns
blendv_ps(v128, v128, v128)
Blend packed single-precision (32-bit) floating-point elements from "a" and "b" using "mask", and store the results in "dst".
Declaration
public static v128 blendv_ps(v128 a, v128 b, v128 mask)
Parameters
Returns
ceil_pd(v128)
Round the packed double-precision (64-bit) floating-point elements in "a" up to an integer value, and store the results as packed double-precision floating-point elements in "dst".
Declaration
public static v128 ceil_pd(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
ceil_ps(v128)
Round the packed single-precision (32-bit) floating-point elements in "a" up to an integer value, and store the results as packed single-precision floating-point elements in "dst".
Declaration
public static v128 ceil_ps(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
ceil_sd(v128, v128)
Round the lower double-precision (64-bit) floating-point element in "b" up to an integer value, store the result as a double-precision floating-point element in the lower element of "dst", and copy the upper element from "a" to the upper element of "dst".
Declaration
public static v128 ceil_sd(v128 a, v128 b)
Parameters
Returns
ceil_ss(v128, v128)
Round the lower single-precision (32-bit) floating-point element in "b" up to an integer value, store the result as a single-precision floating-point element in the lower element of "dst", and copy the upper 3 packed elements from "a" to the upper elements of "dst".
Declaration
public static v128 ceil_ss(v128 a, v128 b)
Parameters
Returns
cmpeq_epi64(v128, v128)
Compare packed 64-bit integers in "a" and "b" for equality, and store the results in "dst".
Declaration
public static v128 cmpeq_epi64(v128 a, v128 b)
Parameters
Returns
cvtepi16_epi32(v128)
Sign extend packed 16-bit integers in "a" to packed 32-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepi16_epi32(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepi16_epi64(v128)
Sign extend packed 16-bit integers in "a" to packed 64-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepi16_epi64(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepi32_epi64(v128)
Sign extend packed 32-bit integers in "a" to packed 64-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepi32_epi64(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepi8_epi16(v128)
Sign extend packed 8-bit integers in "a" to packed 16-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepi8_epi16(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepi8_epi32(v128)
Sign extend packed 8-bit integers in "a" to packed 32-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepi8_epi32(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepi8_epi64(v128)
Sign extend packed 8-bit integers in the low 8 bytes of "a" to packed 64-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepi8_epi64(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepu16_epi32(v128)
Zero extend packed unsigned 16-bit integers in "a" to packed 32-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepu16_epi32(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepu16_epi64(v128)
Zero extend packed unsigned 16-bit integers in "a" to packed 64-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepu16_epi64(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepu32_epi64(v128)
Zero extend packed unsigned 32-bit integers in "a" to packed 64-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepu32_epi64(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepu8_epi16(v128)
Zero extend packed unsigned 8-bit integers in "a" to packed 16-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepu8_epi16(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepu8_epi32(v128)
Zero extend packed unsigned 8-bit integers in "a" to packed 32-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepu8_epi32(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
cvtepu8_epi64(v128)
Zero extend packed unsigned 8-bit integers in the low 8 byte sof "a" to packed 64-bit integers, and store the results in "dst".
Declaration
public static v128 cvtepu8_epi64(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
dp_pd(v128, v128, Int32)
Conditionally multiply the packed double-precision (64-bit) floating-point elements in "a" and "b" using the high 4 bits in "imm8", sum the four products, and conditionally store the sum in "dst" using the low 4 bits of "imm8".
Declaration
public static v128 dp_pd(v128 a, v128 b, int imm8)
Parameters
Returns
dp_ps(v128, v128, Int32)
Conditionally multiply the packed single-precision (32-bit) floating-point elements in "a" and "b" using the high 4 bits in "imm8", sum the four products, and conditionally store the sum in "dst" using the low 4 bits of "imm8".
Declaration
public static v128 dp_ps(v128 a, v128 b, int imm8)
Parameters
Returns
Extract a 32-bit integer from "a", selected with "imm8", and store the result in "dst".
Declaration
public static int extract_epi32(v128 a, int imm8)
Parameters
Returns
Extract a 64-bit integer from "a", selected with "imm8", and store the result in "dst".
Declaration
public static long extract_epi64(v128 a, int imm8)
Parameters
Returns
Extract an 8-bit integer from "a", selected with "imm8", and store the result in the lower element of "dst".
Declaration
public static byte extract_epi8(v128 a, int imm8)
Parameters
Returns
Extract a single-precision (32-bit) floating-point element from "a", selected with "imm8", and store the result in "dst".
Declaration
public static int extract_ps(v128 a, int imm8)
Parameters
Returns
Extract a single-precision (32-bit) floating-point element from "a", selected with "imm8", and store the result in "dst" (as a float).
Declaration
public static float extractf_ps(v128 a, int imm8)
Parameters
Returns
floor_pd(v128)
Round the packed double-precision (64-bit) floating-point elements in "a" down to an integer value, and store the results as packed double-precision floating-point elements in "dst".
Declaration
public static v128 floor_pd(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
floor_ps(v128)
Round the packed single-precision (32-bit) floating-point elements in "a" down to an integer value, and store the results as packed single-precision floating-point elements in "dst".
Declaration
public static v128 floor_ps(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
floor_sd(v128, v128)
Round the lower double-precision (64-bit) floating-point element in "b" down to an integer value, store the result as a double-precision floating-point element in the lower element of "dst", and copy the upper element from "a" to the upper element of "dst".
Declaration
public static v128 floor_sd(v128 a, v128 b)
Parameters
Returns
floor_ss(v128, v128)
Round the lower single-precision (32-bit) floating-point element in "b" down to an integer value, store the result as a single-precision floating-point element in the lower element of "dst", and copy the upper 3 packed elements from "a" to the upper elements of "dst".
Declaration
public static v128 floor_ss(v128 a, v128 b)
Parameters
Returns
insert_epi32(v128, Int32, Int32)
Copy "a" to "dst", and insert the 32-bit integer "i" into "dst" at the location specified by "imm8".
Declaration
public static v128 insert_epi32(v128 a, int i, int imm8)
Parameters
Returns
insert_epi64(v128, Int64, Int32)
Copy "a" to "dst", and insert the 64-bit integer "i" into "dst" at the location specified by "imm8".
Declaration
public static v128 insert_epi64(v128 a, long i, int imm8)
Parameters
Returns
insert_epi8(v128, Byte, Int32)
Copy "a" to "dst", and insert the lower 8-bit integer from "i" into "dst" at the location specified by "imm8".
Declaration
public static v128 insert_epi8(v128 a, byte i, int imm8)
Parameters
Returns
insert_ps(v128, v128, Int32)
Copy "a" to "tmp", then insert a single-precision (32-bit) floating-point element from "b" into "tmp" using the control in "imm8". Store "tmp" to "dst" using the mask in "imm8" (elements are zeroed out when the corresponding bit is set).
Declaration
public static v128 insert_ps(v128 a, v128 b, int imm8)
Parameters
Returns
max_epi32(v128, v128)
Compare packed 32-bit integers in "a" and "b", and store packed maximum values in "dst".
Declaration
public static v128 max_epi32(v128 a, v128 b)
Parameters
Returns
max_epi8(v128, v128)
Compare packed 8-bit integers in "a" and "b", and store packed maximum values in "dst".
Declaration
public static v128 max_epi8(v128 a, v128 b)
Parameters
Returns
max_epu16(v128, v128)
Compare packed unsigned 16-bit integers in "a" and "b", and store packed maximum values in "dst".
Declaration
public static v128 max_epu16(v128 a, v128 b)
Parameters
Returns
max_epu32(v128, v128)
Compare packed unsigned 32-bit integers in "a" and "b", and store packed maximum values in "dst".
Declaration
public static v128 max_epu32(v128 a, v128 b)
Parameters
Returns
min_epi32(v128, v128)
Compare packed 32-bit integers in "a" and "b", and store packed minimum values in "dst".
Declaration
public static v128 min_epi32(v128 a, v128 b)
Parameters
Returns
min_epi8(v128, v128)
Compare packed 8-bit integers in "a" and "b", and store packed minimum values in "dst".
Declaration
public static v128 min_epi8(v128 a, v128 b)
Parameters
Returns
min_epu16(v128, v128)
Compare packed unsigned 16-bit integers in "a" and "b", and store packed minimum values in "dst".
Declaration
public static v128 min_epu16(v128 a, v128 b)
Parameters
Returns
min_epu32(v128, v128)
Compare packed unsigned 32-bit integers in "a" and "b", and store packed minimum values in "dst".
Declaration
public static v128 min_epu32(v128 a, v128 b)
Parameters
Returns
minpos_epu16(v128)
Horizontally compute the minimum amongst the packed unsigned 16-bit integers in "a", store the minimum and index in "dst", and zero the remaining bits in "dst".
Declaration
public static v128 minpos_epu16(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
MK_INSERTPS_NDX(Int32, Int32, Int32)
Helper macro to create index-parameter value for insert_ps
Declaration
public static int MK_INSERTPS_NDX(int srcField, int dstField, int zeroMask)
Parameters
Returns
mpsadbw_epu8(v128, v128, Int32)
Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in "a" compared to those in "b", and store the 16-bit results in "dst".
Declaration
public static v128 mpsadbw_epu8(v128 a, v128 b, int imm8)
Parameters
Returns
mul_epi32(v128, v128)
Multiply the low 32-bit integers from each packed 64-bit element in "a" and "b", and store the signed 64-bit results in "dst".
Declaration
public static v128 mul_epi32(v128 a, v128 b)
Parameters
Returns
mullo_epi32(v128, v128)
Multiply the packed 32-bit integers in "a" and "b", producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in "dst".
Declaration
public static v128 mullo_epi32(v128 a, v128 b)
Parameters
Returns
packus_epi32(v128, v128)
Convert packed 32-bit integers from "a" and "b" to packed 16-bit integers using unsigned saturation, and store the results in "dst".
Declaration
public static v128 packus_epi32(v128 a, v128 b)
Parameters
Returns
round_pd(v128, Int32)
Round the packed double-precision (64-bit) floating-point elements in "a" using the "rounding" parameter, and store the results as packed double-precision floating-point elements in "dst".
Declaration
public static v128 round_pd(v128 a, int rounding)
Parameters
Returns
round_ps(v128, Int32)
Round the packed single-precision (32-bit) floating-point elements in "a" using the "rounding" parameter, and store the results as packed single-precision floating-point elements in "dst".
Declaration
public static v128 round_ps(v128 a, int rounding)
Parameters
Returns
round_sd(v128, v128, Int32)
Round the lower double-precision (64-bit) floating-point element in "b" using the "rounding" parameter, store the result as a double-precision floating-point element in the lower element of "dst", and copy the upper element from "a" to the upper element of "dst".
Declaration
public static v128 round_sd(v128 a, v128 b, int rounding)
Parameters
Returns
round_ss(v128, v128, Int32)
Round the lower single-precision (32-bit) floating-point element in "b" using the "rounding" parameter, store the result as a single-precision floating-point element in the lower element of "dst", and copy the upper 3 packed elements from "a" to the upper elements of "dst".
Declaration
public static v128 round_ss(v128 a, v128 b, int rounding)
Parameters
Returns
stream_load_si128(Void*)
Load 128-bits of integer data from memory into dst using a non-temporal memory hint. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
Declaration
public static v128 stream_load_si128(void *mem_addr)
Parameters
| Type |
Name |
Description |
| Void* |
mem_addr |
|
Returns
test_all_ones(v128)
Compute the bitwise NOT of "a" and then AND with a 128-bit vector containing all 1's, and return 1 if the result is zero, otherwise return 0.>
Declaration
public static int test_all_ones(v128 a)
Parameters
| Type |
Name |
Description |
| v128 |
a |
|
Returns
test_all_zeros(v128, v128)
Compute the bitwise AND of 128 bits (representing integer data) in "a" and "mask", and return 1 if the result is zero, otherwise return 0.
Declaration
public static int test_all_zeros(v128 a, v128 mask)
Parameters
Returns
test_mix_ones_zeroes(v128, v128)
Compute the bitwise AND of 128 bits (representing integer data) in "a" and "mask", and set "ZF" to 1 if the result is zero, otherwise set "ZF" to 0. Compute the bitwise NOT of "a" and then AND with "mask", and set "CF" to 1 if the result is zero, otherwise set "CF" to 0. Return 1 if both the "ZF" and "CF" values are zero, otherwise return 0.
Declaration
public static int test_mix_ones_zeroes(v128 a, v128 mask)
Parameters
Returns
testc_si128(v128, v128)
Compute the bitwise AND of 128 bits (representing integer data) in "a" and "b", and set "ZF" to 1 if the result is zero, otherwise set "ZF" to 0. Compute the bitwise NOT of "a" and then AND with "b", and set "CF" to 1 if the result is zero, otherwise set "CF" to 0. Return the "CF" value.
Declaration
public static int testc_si128(v128 a, v128 b)
Parameters
Returns
testnzc_si128(v128, v128)
Compute the bitwise AND of 128 bits (representing integer data) in "a" and "b", and set "ZF" to 1 if the result is zero, otherwise set "ZF" to 0. Compute the bitwise NOT of "a" and then AND with "b", and set "CF" to 1 if the result is zero, otherwise set "CF" to 0. Return 1 if both the "ZF" and "CF" values are zero, otherwise return 0.
Declaration
public static int testnzc_si128(v128 a, v128 b)
Parameters
Returns
testz_si128(v128, v128)
Compute the bitwise AND of 128 bits (representing integer data) in "a" and "b", and set "ZF" to 1 if the result is zero, otherwise set "ZF" to 0. Compute the bitwise NOT of "a" and then AND with "b", and set "CF" to 1 if the result is zero, otherwise set "CF" to 0. Return the "ZF" value.
Declaration
public static int testz_si128(v128 a, v128 b)
Parameters
Returns