Conditional Select Operators

Intel® C++ Compiler Classic Developer Guide and Reference

Download PDF

ID 767249

Date 3/31/2023

Version

Public

A newer version of this document is available. Customers should click here to go to the newest version.

Visible to Intel only — GUID: GUID-4A6AFD3E-C7E5-4666-8A0F-AE0661A4D726

View Details

Conditional Select Operators

For conditional select operands, the third and fourth operands determine the type returned. Third and fourth operands with same size, but different signedness, return the nearest common ancestor data type.

Conditional Select Syntax Usage

Return the nearest common ancestor data type if third and fourth operands are of the same size, but different signs.

I16vec4 R = select_neq(Is16vec4, Is16vec4, Is16vec4, Iu16vec4);

Conditional Select for Equality

R0 := (A0 == B0) ? C0 : D0;

R1 := (A1 == B1) ? C1 : D1;

R2 := (A2 == B2) ? C2 : D2;

R3 := (A3 == B3) ? C3 : D3;

Conditional Select for Inequality

R0 := (A0 != B0) ? C0 : D0;

R1 := (A1 != B1) ? C1 : D1;

R2 := (A2 != B2) ? C2 : D2;

R3 := (A3 != B3) ? C3 : D3;

Conditional Select Symbols and Corresponding Intrinsics

Conditional Select For:	Operators	Syntax	Corresponding Intrinsic	Additional Intrinsic (Applies to All)
Equality	select_eq	`R = select_eq(A, B, C, D)`	_mm_cmpeq_pi32 _mm_cmpeq_pi16 _mm_cmpeq_pi8	_mm_and_si64 _mm_or_si64 _mm_andnot_si64
Inequality	select_neq	`R = select_neq(A, B, C, D)`	_mm_cmpeq_pi32 _mm_cmpeq_pi16 _mm_cmpeq_pi8
Greater Than	select_gt	`R = select_gt(A, B, C, D)`	_mm_cmpgt_pi32 _mm_cmpgt_pi16 _mm_cmpgt_pi8
Greater Than or Equal To	select_ge	`R = select_gt(A, B, C, D)`	_mm_cmpge_pi32 _mm_cmpge_pi16 _mm_cmpge_pi8
Less Than	select_lt	`R = select_lt(A, B, C, D)`	_mm_cmplt_pi32 _mm_cmplt_pi16 _mm_cmplt_pi8
Less Than or Equal To	select_le	`R = select_le(A, B, C, D)`	_mm_cmple_pi32 _mm_cmple_pi16 _mm_cmple_pi8

All conditional select operands must be of the same size. The return data type is the nearest common ancestor of operands C and D. For conditional select operations using greater-than or less-than operations, the first and second operands must be signed as listed in the table that follows.

Conditional Select Operator Overloading

R	Comparison	A and B	C	D
I32vec2 R	select_eq select_ne	I[s\|u]32vec2	I[s\|u]32vec2	I[s\|u]32vec2
I16vec4 R			I[s\|u]16vec4	I[s\|u]16vec4
I8vec8 R			I[s\|u]8vec8	I[s\|u]8vec8
I32vec2 R	select_gt select_ge select_lt select_le	Is32vec2	Is32vec2	Is32vec2
I16vec4 R			Is16vec4	Is16vec4
I8vec8 R			Is8vec8	Is8vec8

The following table shows the mapping of return values from R0 to R7 for any number of elements. The same return value mappings also apply when there are fewer than four return values.

Conditional Select Operator Return Value Mapping

Return Value	A Operands	Available Operators						B Operands	C and D Operands
R0:=	A0	==	!=	>	>=	<	<=	B0	C0 : D0;
R1:=	A0	==	!=	>	>=	<	<=	B0	C1 : D1;
R2:=	A0	==	!=	>	>=	<	<=	B0	C2 : D2;
R3:=	A0	==	!=	>	>=	<	<=	B0	C3 : D3;
R4:=	A0	==	!=	>	>=	<	<=	B0	C4 : D4;
R5:=	A0	==	!=	>	>=	<	<=	B0	C5 : D5;
R6:=	A0	==	!=	>	>=	<	<=	B0	C6 : D6;
R7:=	A0	==	!=	>	>=	<	<=	B0	C7 : D7;

Parent topic: Integer Vector Classes

Select Your Language

Using Intel.com Search

Quick Links

Recent Searches

Advanced Search

Only search in

Intel® C++ Compiler Classic Developer Guide and Reference

Conditional Select Operators