Vesta
English
Source code

VMAXSH

Return Maximum of Scalar FP16 Values

stableVMJITAOTinstruction

Encodings

OpcodeInstructionOp/En64-bitCompat/LegacyDescription
EVEX.LLIG.F3.MAP5.W0 5F /rVMAXSH xmm1{k1}{z}, xmm2, xmm3/m16 {sae}AValidValidReturn the maximum low FP16 value between OR AVX10.1 xmm3/m16 and xmm2 and store the result in xmm1 subject to writemask k1. Bits 127:16 of xmm2 are copied to xmm1[127:16].

Operand encoding

Each mode is a value of the Op/En column above. It says which field of the encoded instruction carries each operand, in the order they are written, and whether the instruction reads it, writes it or both.

A

  1. modrm.reg escrituraModRM byte, reg field (bits 5-3)
  2. vex.vvvv lecturaVEX prefix, vvvv field (inverted)
  3. modrm.rm lecturaModRM byte, r/m field (bits 2-0); with the SIB byte and the displacement when the mod field asks for them

Tupla: Scalar

Measured cost

Loading measurements from arch-data...

Description

This instruction performs a compare of the low packed FP16 values in the first source operand and the second source operand and returns the maximum value for the pair of values to the destination operand.

If the values being compared are both 0.0s (of either sign), the value in the second operand (source operand) is returned. If a value in the second operand is an SNaN, then SNaN is forwarded unchanged to the destination (that is, a QNaN version of the SNaN is not returned).

If only one value is a NaN (SNaN or QNaN) for this instruction, the second operand (source operand), either a NaN or a valid floating-point value, is written to the result. If instead of this behavior, it is required that the NaN source operand (from either the first or second operand) be returned, the action of VMAXSH can be emulated using a sequence of instructions, such as, a comparison followed by AND, ANDN, and OR.

Bits 127:16 of the destination operand are copied from the corresponding bits of the first source operand. Bits MAXVL-1:128 of the destination operand are zeroed. The low FP16 element of the destination is updated according to the writemask.

Operation

def MAX(SRC1, SRC2):
    IF (SRC1 = 0.0) and (SRC2 = 0.0):
          DEST := SRC2
    ELSE IF (SRC1 = NaN):
          DEST := SRC2
    ELSE IF (SRC2 = NaN):
          DEST := SRC2
    ELSE IF (SRC1 > SRC2):
          DEST := SRC1
    ELSE:
          DEST := SRC2


VMAXSH dest, src1, src2
IF k1[0] OR *no writemask*:

    DEST.fp16[0] := MAX(SRC1.fp16[0], SRC2.fp16[0])
ELSE IF *zeroing*:

    DEST.fp16[0] := 0
// else dest.fp16[j] remains unchanged

DEST[127:16] := SRC1[127:16]
DEST[MAXVL-1:128] := 0

Intel C/C++ compiler intrinsics

VMAXSH __m128h _mm_mask_max_round_sh (__m128h src, __mmask8 k, __m128h a, __m128h b, int sae);
VMAXSH __m128h _mm_maskz_max_round_sh (__mmask8 k, __m128h a, __m128h b, int sae);
VMAXSH __m128h _mm_max_round_sh (__m128h a, __m128h b, int sae);
VMAXSH __m128h _mm_mask_max_sh (__m128h src, __mmask8 k, __m128h a, __m128h b);
VMAXSH __m128h _mm_maskz_max_sh (__mmask8 k, __m128h a, __m128h b);
VMAXSH __m128h _mm_max_sh (__m128h a, __m128h b);

SIMD Floating-Point Exceptions

Invalid, Denormal

Other Exceptions

EVEX-encoded instructions, see Table 2-49, "Type E3 Class Exception Conditions."

Sources