_mm512_cmp_ps_mask/ _mm512_mask_cmp_ps

Performs a comparison between float32 vectors. Corresponding instruction is VCMPPS. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).

Syntax

Without Mask

extern __mmask16 __cdecl _mm512_cmp_ps_mask(__m512 v2, __m512 v3, const int op);

With Mask

extern __mmask16 __cdecl _mm512_mask_cmp_ps_mask(__mmask16 k1, __m512 v2, __m512 v3, const int op);

Parameters

`v2`	float32 vector used for the compare operation
`v3`	float32 vector used for the compare operation
`k1`	Writemask; only those elements of the source vectors with corresponding bit set to '1' in the `k1` mask are computed and stored in the result
`op`	Comparison predicate. Takes one of the following values: `_MM_CMPINT_EQ` - Equal `_MM_CMPINT_LT` - Less than `_MM_CMPINT_LE` - Less than or Equal `_MM_CMPINT_NE` - Not Equal `_MM_CMPINT_NLT` - Not Less than `_MM_CMPINT_GE` - Greater than or Equal `_MM_CMPINT_NLE` - Not Less than or Equal `_MM_CMPINT_GT` - Greater than

Description

This intrinsic performs an element-by-element comparison between float32 vectors v2 and v3, using the op parameter as a comparison predicate.

For the sake of convenience, the compiler provides the following intrinsics that correspond to the values of the op parameter. You can use these intrinsic names instead of specifying the op parameter.

Intrinsic Name	Corresponding Comparison Predicate
`_mm512_cmpeq_ps_mask(v2, v3)`	`_CMP_EQ_OQ`
`_mm512_mask_cmpeq_ps_mask(k1, v2, v3)`	`_CMP_EQ_OQ`
`_mm512_cmplt_ps_mask(v2, v3)`	`_CMP_LT_OS`
`_mm512_mask_cmplt_ps_mask(k1, v2, v3)`	`_CMP_LT_OS`
`_mm512_cmple_ps_mask(v2, v3)`	`_CMP_LE_OS`
`_mm512_mask_cmple_ps_mask(k1, v2, v3)`	`_CMP_LE_OS`
`_mm512_cmpunord_ps_mask(v2, v3)`	`_CMP_UNORD_Q`
`_mm512_mask_cmpunord_ps_mask(k1, v2, v3)`	`_CMP_UNORD_Q`
`_mm512_cmpneq_ps_mask(v2, v3)`	`_CMP_NEQ_UQ`
`_mm512_mask_cmpneq_ps_mask(k1, v2, v3)`	`_CMP_NEQ_UQ`
`_mm512_cmpnlt_ps_mask(v2, v3)`	`_CMP_NLT_US`
`_mm512_mask_cmpnlt_ps_mask(k1, v2, v3)`	`_CMP_NLT_US`
`_mm512_cmpnle_ps_mask(v2, v3)`	`_CMP_NLE_US`
`_mm512_mask_cmpnle_ps_mask(k1, v2, v3)`	`_CMP_NLE_US`
`_mm512_cmpord_ps_mask(v2, v3)`	`_CMP_ORD_Q`
`_mm512_mask_cmpord_ps_mask(k1, v2, v3)`	`_CMP_ORD_Q`

Returns

Returns the result of the comparison in bit eight of the return value, where there is one bit per pair of elements. The ith bit is set to one if and only if (v2[i] op v3[i]) is true.

In the masked variant, for those elements with a corresponding mask bit set to zero, the return value in the corresponding bit of the result mask is zero.

_mm512_cmp_ps_mask/ _mm512_mask_cmp_ps_mask

Syntax

Parameters

Description

Returns