03.03.2013 Views

Intel® Architecture Instruction Set Extensions Programming Reference

Intel® Architecture Instruction Set Extensions Programming Reference

Intel® Architecture Instruction Set Extensions Programming Reference

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

VBROADCAST — Broadcast Floating-Point Data<br />

Opcode/<br />

<strong>Instruction</strong><br />

Description<br />

<strong>Instruction</strong> Operand Encoding<br />

INSTRUCTION SET REFERENCE<br />

Take the low floating-point data element from the source operand (second operand) and broadcast to all elements<br />

of the destination operand (first operand).<br />

The destination operand is a YMM register. The source operand is an XMM register, only the low 32-bit or 64-bit<br />

data element is used.<br />

Note: In VEX-encoded versions, VEX.vvvv is reserved and must be 1111b otherwise instructions will #UD.<br />

An attempt to execute VBROADCASTSD encoded with VEX.L= 0 will cause an #UD exception.<br />

Operation<br />

VBROADCASTSS (128 bit version)<br />

temp SRC[31:0]<br />

FOR j 0 TO 3<br />

DEST[31+j*32: j*32] temp<br />

ENDFOR<br />

DEST[VLMAX:128] 0<br />

Op/<br />

En<br />

64/32<br />

-bit<br />

Mode<br />

VBROADCASTSS (VEX.256 encoded version)<br />

temp SRC[31:0]<br />

FOR j 0 TO 7<br />

DEST[31+j*32: j*32] temp<br />

ENDFOR<br />

CPUID<br />

Feature<br />

Flag<br />

Description<br />

VEX.128.66.0F38.W0 18 /r A V/V AVX Broadcast single-precision floating-point element in mem to four locations<br />

in xmm1.<br />

VBROADCASTSS xmm1, m32<br />

VEX.256.66.0F38.W0 18 /r A V/V AVX Broadcast single-precision floating-point element in mem to eight locations<br />

in ymm1.<br />

VBROADCASTSS ymm1, m32<br />

VEX.256.66.0F38.W0 19 /r A V/V AVX Broadcast double-precision floating-point element in mem to four locations<br />

in ymm1.<br />

VBROADCASTSD ymm1, m64<br />

VEX.128.66.0F38.W0 18/r A V/V AVX2 Broadcast the low single-precision floating-point element in the<br />

source operand to four locations in xmm1.<br />

VBROADCASTSS xmm1,<br />

xmm2<br />

VEX.256.66.0F38.W0 18 /r A V/V AVX2 Broadcast low single-precision floating-point element in the source<br />

operand to eight locations in ymm1.<br />

VBROADCASTSS ymm1,<br />

xmm2<br />

VEX.256.66.0F38.W0 19 /r A V/V AVX2 Broadcast low double-precision floating-point element in the source<br />

operand to four locations in ymm1.<br />

VBROADCASTSD ymm1,<br />

xmm2<br />

Op/En Operand 1 Operand 2 Operand 3 Operand 4<br />

A ModRM:reg (w) ModRM:r/m (r) NA NA<br />

Ref. # 319433-014 5-175

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!