EVEX prefix

From Wikipedia, the free encyclopedia
Jump to: navigation, search

The EVEX prefix (Enhanced vector extension) and corresponding coding scheme is an extension to the 32-bit x86 (IA-32) and 64-bit x86-64 (Intel 64) instruction set architecture for Intel microprocessors. EVEX is based on, but should not be confused with the MVEX prefix used by the Knights Corner processor.

The EVEX scheme is a 4-byte extension to the VEX scheme which supports the AVX-512 instruction set and allows addressing new 512-bit ZMM registers and new 64-bit operand mask registers.

Features[edit]

EVEX coding can address 8 operand mask registers, 16 general-purpose registers and 32 vector registers in 64-bit mode (otherwise, 8 general-purpose and 8 vector), and can support up to 4 operands.

Like the VEX coding scheme, the EVEX prefix unifies existing opcode prefixes and escape codes, memory addressing and operand length modifiers of the x86 instruction set .

The following features are carried over from the VEX scheme:

  • Direct encoding of three SIMD registers (XMM, YMM, or ZMM) as source operands (MMX or x87 registers are not supported);
  • Compacted REX prefix for 64-bit mode;
  • Compacted SIMD prefix (66H, F2H, F3H), escape opcode (0FH) and two-byte escape (0F38H, 0F3AH);
  • Less strict memory alignment requirements for memory operand

EVEX also extends VEX with additional capabilities:

  • Extended SIMD register encoding: a total of 32 new 512-bit SIMD registers ZMM0-ZMM31 in 64-bit mode;
  • Operand mask encoding: 8 new 64-bit opmask registers k0-k7 for conditional execution and merging of destination operands;
  • Broadcasting from source to destination for instructions that take memory vector as a source operand: the second operand is broadcast before being used in the actual operation;
  • Direct embedded rounding control for instructions that operate on floating-point SIMD registers with rounding semantics;
  • Embedded exceptions control for floating-point instructions without rounding semantics;
  • Compressed displacement (DISP8*N), new memory addressing mode to improve encoding density of instruction byte stream; the scale factor N depends on vector length and broadcast mode.

For example, the EVEX encoding scheme allows conditional vector addition in the form of

VADDPS zmm1 {k1}{z}, zmm2, zmm3

where {k1} modifier next to the destination operand encodes the use of opmask register k1 for conditional processing and updates to destination, and {z} modifier (encoded by EVEX.z) provides the two types of masking (merging and zeroing), with merging as default when no modifier is attached.

Technical description[edit]

The EVEX coding scheme uses a code prefix consisting of 4 bytes; the first byte is always 62h and derives from an unused opcode of the 32-bit BOUND instruction, which is not supported in 64-bit mode. [1]

EVEX Prefix in the AVX-512 Instruction Format
# of bytes 4 1 1 1 4 / 1 1
[Prefixes] EVEX Opcode ModR/M [SIB] [Disp32] / [Disp8*N] [Immediate]

The ModR/M byte specifies the addressing of the source register with mod and r/m fields, which encode either 8 registers or 24 addressing modes, and the destination register is encoded with reg field. Base-plus-index and scale-plus-index addressing require the SIB byte, which encodes 2-bit scale factor as well as 3-bit index and 3-bit base registers. In certain SIB encodings, Disp32 contains displacements that need to be added to the base address.

The EVEX prefix retains some fields introduced in the VEX prefix:

  • Four bits R, X, B, and W from the REX prefix. W expands the operand size to 64 bits or serves as an additional opcode, R expands reg, B expands r/m or reg, and X and B expand index and base in the SIB byte. Comparing to the VEX prefix, RXB are provided in non-inversed forms.
  • Four bits named v, specifying a second non-destructive source register operand.
  • Bit L specifying 256-bit vector length.
  • Two bits named p to replace operand size prefixes and operand type prefixes (66, F2, F3).
  • Two of the m bits for replacing existing escape codes (0F, 0F 38 and 0F 3A;).
  • Bit V' is an additional source register index.

New functions of the existing fields:

  • Bit X now expands reg or r/m along with bit B when the SIB byte is not present.

There are several new bit fields:

  • Three bits named a, specifying the operand mask register (k0-k7) for vector instructions.
  • Bit z for specifying merging mode (merge or zero).
  • Bit b for source broadcast, rounding control (combined with L’L), or suppress exceptions
  • Bit L’ for specifying 512-bit vector length, or rounding control mode when combined with L
  • Bit R’ for expanding reg, which allows for 32 SIMD registers

The encoding of the EVEX prefix is as follows:

7 6 5 4 3 2 1 0
Byte 0 (62h) 0 1 1 0 0 0 1 0
Byte 1 (P1) R X B R’ 0 0 m1 m0 P[7:0]
Byte 2 (P2) W v3 v2 v1 v0 1 p1 p0 P[15:8]
Byte 3 (P3) z L’ L b V’ a2 a1 a0 P[23:16]

The following table lists allowed register addressing combinations (bit 4 is always zero when encoding the 16 general purpose registers):

Register addressing in 64-bit mode using EVEX prefix
Addressing mode Bit 4 Bit 3 Bits [2:0] Register type Common usage
REG EVEX.R’ EVEX.R ModRM.reg General purpose, Vector Destination or Source
NDS/NDD EVEX.V’ EVEX.v3v2v1v0 GPR, Vector 2nd Source or Destination
RM EVEX.X EVEX.B ModRM.r/m GPR, Vector 1st Source or Destination
BASE 0 EVEX.B ModRM.r/m GPR Memory addressing
INDEX 0 EVEX.X SIB.index GPR Memory addressing
VIDX EVEX.V’ EVEX.X SIB.index Vector VSIB memory addressing
IS4 Imm8[3] Imm8[7:4] Vector 3rd Source

References[edit]