VFNMSUB231PD

VFNMSUB231PD computes -(op2 × op3) - op1 for each double, rounded once: both the product and the destination’s old value are negated. It is the double form of VFNMSUB231PS, which shows why the instruction is not a VFMADD with its result negated, and VFNMADD231PS sets the four sign variants side by side. VFMADD231PS explains the three digits and what the EVEX forms add.

In our builds#

At -O2 with -ffast-math, Clang 23 compiles s -= x[i] * y[i] over doubles as it does over floats: VMULPD for one pair, VFNMSUB231PD to fold in the next, -(x × y) - p, and VADDPD into one of four ymm sums, for both -march=x86-64-v3 and -v4. GCC 14 uses VFNMADD231PD on a zmm sum for -v4 instead.

Recorded on Zen 5#

• In vfnmsub231pd xmm7, xmm11, xmmword ptr [mem] under MXCSR 7F80H (toward zero), -(3 × 0.1) - (-0.3) returned -2^-55, BC80000000000000H: the error of rounding the product 3 × 0.1 to a double, which VFMADD213PD shows with the opposite sign.
• -(10^300 × 10^300) minus a value of 10^300 overflows. Under 3FC0H (round down), vfnmsub231pd xmm7, xmm11, xmm7 subtracted 10^300 and returned minus infinity; under 7F80H, vfnmsub231pd ymm0, ymm13, ymmword ptr [mem] subtracted -10^300 and returned the most negative finite double. Both set OE and PE.

AMD’s latency spreadsheet for Zen 5 gives the VEX and the EVEX rows alike a latency of 4 cycles, two per cycle on pipes FP0 and FP1.

Forms

Latency and throughput

Data flow

Where the elements of the sources go, element 0 on the right; results that depend on a control value are drawn for an example. How to read.

Operation

What the forms do, in pseudocode that our tests run against results recorded on real processors. How to read.

for i in range(VL // 64):
    if k1[i]:  # 1 without a write mask
        a = zmm1.f64[i]
        b = zmm2.f64[i]
        c = src3.f64[i]
        zmm1.f64[i] = fnmsub(b, c, a)
    elif zeroing:
        zmm1.f64[i] = 0
    # else: zmm1.f64[i] keeps its value
# m64bcst: src3.f64[i] is the m64 for every i
# {er}: the form's rounding, not MXCSR.RC, and no flags
# zmm1 is zeroed from bit VL up

Operands

Flags

None: XED records no flag that the forms test or change.

Exceptions

The exception class is XED's name for the set of exception conditions that a form follows. How to read.

VEX forms

avx-type-2

EVEX forms

AVX512-E2

Attributes

What else XED records about the forms. How to read.

All forms

follows MXCSR

EVEX forms

write masking

EVEX memory forms

embedded broadcast (tuple Full); memory fault suppression

Intrinsics

The C intrinsics of Clang 23.1.2 that compile to VFNMSUB231PD, each with the form it compiles to and the Clang options it needs. The forms come from compiling every intrinsic and decoding the result with Intel XED; all intrinsics A–Z explains the method.

CPUID and processors

Each form belongs to an XED ISA set. A form can be used when the processor reports every CPUID bit of one of its ISA set's alternatives.

More FMA instructions

• VFMSUB132PS
• VFMSUB132SD
• VFMSUB132SS
• VFMSUB213PD
• VFMSUB213PS
• VFMSUB213SD
• VFMSUB213SS
• VFMSUB231PD
• VFMSUB231PS
• VFMSUB231SD
• VFMSUB231SS
• VFMSUBADD132PD
• VFMSUBADD132PS
• VFMSUBADD213PD
• VFMSUBADD213PS
• VFMSUBADD231PD
• VFMSUBADD231PS
• VFNMADD132PD
• VFNMADD132PS
• VFNMADD132SD
• VFNMADD132SS
• VFNMADD213PD
• VFNMADD213PS
• VFNMADD213SD
• VFNMADD213SS
• VFNMADD231PD
• VFNMADD231PS
• VFNMADD231SD
• VFNMADD231SS
• VFNMSUB132PD
• VFNMSUB132PS
• VFNMSUB132SD
• VFNMSUB132SS
• VFNMSUB213PD
• VFNMSUB213PS
• VFNMSUB213SD
• VFNMSUB213SS
• VFNMSUB231PS
• VFNMSUB231SD
• VFNMSUB231SS

All 60 FMA instructions

More AVX10.1 instructions

• VFNMADD213SH
• VFNMADD213SS
• VFNMADD231PD
• VFNMADD231PH
• VFNMADD231PS
• VFNMADD231SD
• VFNMADD231SH
• VFNMADD231SS
• VFNMSUB132PD
• VFNMSUB132PH
• VFNMSUB132PS
• VFNMSUB132SD
• VFNMSUB132SH
• VFNMSUB132SS
• VFNMSUB213PD
• VFNMSUB213PH
• VFNMSUB213PS
• VFNMSUB213SD
• VFNMSUB213SH
• VFNMSUB213SS
• VFNMSUB231PH
• VFNMSUB231PS
• VFNMSUB231SD
• VFNMSUB231SH
• VFNMSUB231SS
• VFPCLASSPD
• VFPCLASSPH
• VFPCLASSPS
• VFPCLASSSD
• VFPCLASSSH
• VFPCLASSSS
• VGATHERDPD
• VGATHERDPS
• VGATHERQPD
• VGATHERQPS
• VGETEXPPD
• VGETEXPPH
• VGETEXPPS
• VGETEXPSD
• VGETEXPSH

All 686 AVX10.1 instructions