Vesta
English
Source code

VCVTUQQ2PH

Convert Packed Unsigned Quadword Integers to Packed FP16 Values

stableVMJITAOTinstruction

Encodings

OpcodeInstructionOp/En64-bitCompat/LegacyDescription
EVEX.128.F2.MAP5.W1 7A /rVCVTUQQ2PH xmm1{k1}{z}, xmm2/m128/m64bcstAValidValidConvert two packed unsigned quadword integers AND AVX512VL) from xmm2/m128/m64bcst to packed FP16 OR AVX10.1 values, and store the result in xmm1 subject to writemask k1.
EVEX.256.F2.MAP5.W1 7A /rVCVTUQQ2PH xmm1{k1}{z}, ymm2/m256/m64bcstAValidValidConvert four packed unsigned quadword integers AND AVX512VL) from ymm2/m256/m64bcst to packed FP16 OR AVX10.1 values, and store the result in xmm1 subject to writemask k1.
EVEX.512.F2.MAP5.W1 7A /rVCVTUQQ2PH xmm1{k1}{z}, zmm2/m512/m64bcst {er}AValidValidConvert eight packed unsigned quadword OR AVX10.1 integers from zmm2/m512/m64bcst to packed FP16 values, and store the result in xmm1 subject to writemask k1.

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. 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: Full

Measured cost

Loading measurements from arch-data...

Description

This instruction converts packed unsigned quadword integers in the source operand to packed FP16 values in the destination operand. The destination elements are updated according to the writemask.

EVEX.vvvv is reserved and must be 1111b otherwise instructions will #UD.

If the result of the convert operation is overflow and MXCSR.OM=0 then a SIMD exception will be raised with OE=1, PE=1.

Operation

VCVTUQQ2PH dest, src
VL = 128, 256 or 512
KL := VL / 64

IF *SRC is a register* and (VL = 512) AND (EVEX.b = 1):
    SET_RM(EVEX.RC)

ELSE:
    SET_RM(MXCSR.RC)

FOR j := 0 TO KL-1:
    IF k1[j] OR *no writemask*:
          IF *SRC is memory* and EVEX.b = 1:
                tsrc := SRC.qword[0]
          ELSE
                tsrc := SRC.qword[j]
          DEST.fp16[j] := Convert_unsigned_integer64_to_fp16(tsrc)
    ELSE IF *zeroing*:
          DEST.fp16[j] := 0
    // else dest.fp16[j] remains unchanged

DEST[MAXVL-1:VL/4] := 0

Intel C/C++ compiler intrinsics

VCVTUQQ2PH __m128h _mm512_cvt_roundepu64_ph (__m512i a, int rounding);
VCVTUQQ2PH __m128h _mm512_mask_cvt_roundepu64_ph (__m128h src, __mmask8 k, __m512i a, int rounding);
VCVTUQQ2PH __m128h _mm512_maskz_cvt_roundepu64_ph (__mmask8 k, __m512i a, int rounding);
VCVTUQQ2PH __m128h _mm_cvtepu64_ph (__m128i a);
VCVTUQQ2PH __m128h _mm_mask_cvtepu64_ph (__m128h src, __mmask8 k, __m128i a);
VCVTUQQ2PH __m128h _mm_maskz_cvtepu64_ph (__mmask8 k, __m128i a);
VCVTUQQ2PH __m128h _mm256_cvtepu64_ph (__m256i a);
VCVTUQQ2PH __m128h _mm256_mask_cvtepu64_ph (__m128h src, __mmask8 k, __m256i a);
VCVTUQQ2PH __m128h _mm256_maskz_cvtepu64_ph (__mmask8 k, __m256i a);
VCVTUQQ2PH __m128h _mm512_cvtepu64_ph (__m512i a);
VCVTUQQ2PH __m128h _mm512_mask_cvtepu64_ph (__m128h src, __mmask8 k, __m512i a);
VCVTUQQ2PH __m128h _mm512_maskz_cvtepu64_ph (__mmask8 k, __m512i a);

SIMD Floating-Point Exceptions

Overflow, Precision.

Other Exceptions

EVEX-encoded instructions, see Table 2-48, "Type E2 Class Exception Conditions."

Sources