Skip to content

VZEROUPPER

Henk-Jan Lebbink edited this page Feb 12, 2019 · 14 revisions

VZEROUPPER — Zero Upper Bits of YMM Registers

Opcode/ Instruction Op/ En 64/32 bit Mode Support CPUID Feature Flag Description
VEX.128.0F.WIG 77 VZEROUPPER ZO V/V AVX Zero upper 128 bits of all YMM registers.

Instruction Operand Encoding

Op/En Operand 1 Operand 2 Operand 3 Operand 4
ZO NA NA NA NA

Description

The instruction zeros the bits in position 128 and higher of all YMM registers. The lower 128-bits of the registers (the corresponding XMM registers) are unmodified.

This instruction is recommended when transitioning between AVX and legacy SSE code - it will eliminate performance penalties caused by false dependencies.

Note: VEX.vvvv is reserved and must be 1111b otherwise instructions will #UD. In Compatibility and legacy 32-bit mode only the lower 8 registers are modified.

Operation

simd_reg_file[][] is a two dimensional array representing the SIMD register file containing all the overlapping xmm, ymm and zmm registers present in that implementation. The major dimension is the register number: 0 for xmm0, ymm0 and zmm0; 1 for xmm1, ymm1, and zmm1; etc. The minor dimension size is the width of the implemented SIMD state measured in bits. On a machine supporting Intel AVX-512, the width is 512. On a machine supporting Intel AVX but not Intel AVX-512, the width is “MAXVL”.

VZEROUPPER

IF (64-bit mode)
    limit15
ELSE
    limit7
FOR i in 0 .. limit:
    simd_reg_file[i][MAXVL-1:128] ← 0

Intel C/C++ Compiler Intrinsic Equivalent

VZEROUPPER:
 _mm256_zeroupper()

SIMD Floating-Point Exceptions

None.

Other Exceptions

See Exceptions Type 8.


Source: Intel® Architecture Software Developer's Manual (May 2018)
Generated: 5-6-2018

Clone this wiki locally