core.simd

template Vector(T)

Create a vector type.

Parameters T = one of double[2], float[4], void[16], byte[16], ubyte[16], short[8], ushort[8], int[4], uint[4], long[2], ulong[2]. For 256 bit vectors, one of double[4], float[8], void[32], byte[32], ubyte[32], short[16], ushort[16], int[8], uint[8], long[4], ulong[4]

alias void16 = __vector(void[16]);

alias double2 = __vector(double[2]);

alias float4 = __vector(float[4]);

alias byte16 = __vector(byte[16]);

alias ubyte16 = __vector(ubyte[16]);

alias short8 = __vector(short[8]);

alias ushort8 = __vector(ushort[8]);

alias int4 = __vector(int[4]);

alias uint4 = __vector(uint[4]);

alias long2 = __vector(long[2]);

alias ulong2 = __vector(ulong[2]);

enum XMM: int;

XMM opcodes that conform to the following:

opcode xmm1,xmm2/mem

and do not have side effects (i.e. do not write to memory).

STOSS

MOVSS xmm1/m32, xmm2

STOSD

MOVSD xmm1/m64, xmm2

STOAPS

MOVAPS xmm2/m128, xmm1

STOAPD

MOVAPD xmm2/m128, xmm1

STODQA

MOVDQA xmm2/m128, xmm1

STOD

MOVD reg/mem64, xmm 66 0F 7E /r

STOQ

MOVQ xmm2/m64, xmm1

LODSS

MOVSS xmm1, xmm2/m32

LODSD

MOVSD xmm1, xmm2/m64

LODAPS

MOVAPS xmm1, xmm2/m128

LODAPD

MOVAPD xmm1, xmm2/m128

LODDQA

MOVDQA xmm1, xmm2/m128

LODD

MOVD xmm, reg/mem64 66 0F 6E /r

LODQ

MOVQ xmm1, xmm2/m64

LODDQU

MOVDQU xmm1, xmm2/mem128 F3 0F 6F /r

STODQU

MOVDQU xmm1/mem128, xmm2 F3 0F 7F /r

MOVDQ2Q

MOVDQ2Q mmx, xmm F2 0F D6 /r

MOVHLPS

MOVHLPS xmm1, xmm2 0F 12 /r

LODHPD

MOVHPD xmm1, m64

STOHPD

MOVHPD mem64, xmm1 66 0F 17 /r

LODHPS

MOVHPS xmm1, m64

STOHPS

MOVHPS m64, xmm1

MOVLHPS

MOVLHPS xmm1, xmm2

LODLPD

MOVLPD xmm1, m64

STOLPD

MOVLPD m64, xmm1

LODLPS

MOVLPS xmm1, m64

STOLPS

MOVLPS m64, xmm1

MOVMSKPD

MOVMSKPD reg, xmm

MOVMSKPS

MOVMSKPS reg, xmm

MOVNTDQ

MOVNTDQ m128, xmm1

MOVNTI

MOVNTI m32, r32

MOVNTPD

MOVNTPD m128, xmm1

MOVNTPS

MOVNTPS m128, xmm1

MOVNTQ

MOVNTQ m64, mm

MOVQ2DQ

MOVQ2DQ

LODUPD

MOVUPD xmm1, xmm2/m128

STOUPD

MOVUPD xmm2/m128, xmm1

LODUPS

MOVUPS xmm1, xmm2/m128

STOUPS

MOVUPS xmm2/m128, xmm1

pure nothrow @nogc @safe void16 __simd(XMM opcode, void16 op1, void16 op2);

Generate two operand instruction with XMM 128 bit operands.

This is a compiler magic function - it doesn't behave like regular D functions.

Parameters opcode = any of the XMM opcodes; it must be a compile time constant op1 = first operand op2 = second operand

Returns:

result of opcode

Examples:

float4 a;
a = cast(float4)__simd(XMM.PXOR, a, a);

pure nothrow @nogc @safe void16 __simd(XMM opcode, void16 op1);

Unary SIMD instructions.

pure nothrow @nogc @safe void16 __simd(XMM opcode, double d);

pure nothrow @nogc @safe void16 __simd(XMM opcode, float f);

Examples:

float4 a;
a = cast(float4)__simd(XMM.LODSS, a);

pure nothrow @nogc @safe void16 __simd(XMM opcode, void16 op1, void16 op2, ubyte imm8);

For instructions: CMPPD, CMPSS, CMPSD, CMPPS, PSHUFD, PSHUFHW, PSHUFLW, BLENDPD, BLENDPS, DPPD, DPPS, MPSADBW, PBLENDW, ROUNDPD, ROUNDPS, ROUNDSD, ROUNDSS

Parameters opcode = any of the above XMM opcodes; it must be a compile time constant op1 = first operand op2 = second operand imm8 = third operand; must be a compile time constant

Returns:

result of opcode

Examples:

float4 a;
a = cast(float4)__simd(XMM.CMPPD, a, a, 0x7A);

pure nothrow @nogc @safe void16 __simd_ib(XMM opcode, void16 op1, ubyte imm8);

For instructions with the imm8 version: PSLLD, PSLLQ, PSLLW, PSRAD, PSRAW, PSRLD, PSRLQ, PSRLW, PSRLDQ, PSLLDQ

Parameters opcode = any of the XMM opcodes; it must be a compile time constant op1 = first operand imm8 = second operand; must be a compile time constant

Returns:

result of opcode

Examples:

float4 a;
a = cast(float4) __simd_ib(XMM.PSRLQ, a, 0x7A);

pure nothrow @nogc @safe void16 __simd_sto(XMM opcode, void16 op1, void16 op2);

For "store" operations of the form: op1 op= op2

Returns:

op2 These cannot be marked as pure, as semantic() doesn't check them.

pure nothrow @nogc @safe void16 __simd_sto(XMM opcode, double op1, void16 op2);

pure nothrow @nogc @safe void16 __simd_sto(XMM opcode, float op1, void16 op2);

Examples:

void16 a;
float f = 1;
double d = 1;

cast(void)__simd_sto(XMM.STOUPS, a, a);
cast(void)__simd_sto(XMM.STOUPS, f, a);
cast(void)__simd_sto(XMM.STOUPS, d, a);

void prefetch(bool writeFetch, ubyte locality)(const(void)* address);

Emit prefetch instruction.

Parameters:

const(void)* address	address to be prefetched
writeFetch	true for write fetch, false for read fetch
locality	0..3 (0 meaning least local, 3 meaning most local)

Note The Intel mappings are:

writeFetch	locality	Instruction
false	0	prefetchnta
false	1	prefetch2
false	2	prefetch1
false	3	prefetch0
true	0	prefetchw
true	1	prefetchw
true	2	prefetchw
true	3	prefetchw

V loadUnaligned(V)(const V* p)
if (is(V == void16) || is(V == byte16) || is(V == ubyte16) || is(V == short8) || is(V == ushort8) || is(V == int4) || is(V == uint4) || is(V == long2) || is(V == ulong2) || is(V == double2) || is(V == float4));

Load unaligned vector from address. This is a compiler intrinsic.

Parameters:

V* p	pointer to vector

Returns:

vector

V storeUnaligned(V)(V* p, V value)
if (is(V == void16) || is(V == byte16) || is(V == ubyte16) || is(V == short8) || is(V == ushort8) || is(V == int4) || is(V == uint4) || is(V == long2) || is(V == ulong2) || is(V == double2) || is(V == float4));

Store vector to unaligned address. This is a compiler intrinsic.

Parameters:

V* p	pointer to vector
V value	value to store

Returns:

value