Search all intrinsics
SIMD ISAReturn TypeNameArgumentsInstruction Group
Neonint32x4_tvqshlq_s32(int32x4_t a, int32x4_t b)Shift / Left / Vector saturating shift left
Description
Signed saturating Shift Left (register). This instruction takes each element in the vector of the first source SIMD&FP register, shifts each element by a value from the least significant byte of the corresponding element of the second source SIMD&FP register, places the results in a vector, and writes the vector to the destination SIMD&FP register.
Results
Vd.4S result
This intrinsic compiles to the following instructions:

SQSHL Vd.4S,Vn.4S,Vm.4S

Argument Preparation
a register: Vn.4Sb register: Vm.4S
Architectures
v7, A32, A64

Operation

CheckFPAdvSIMDEnabled64();
bits(datasize) operand1 = V[n];
bits(datasize) operand2 = V[m];
bits(datasize) result;

integer round_const = 0;
integer shift;
integer element;
boolean sat;

for e = 0 to elements-1
    shift = SInt(Elem[operand2, e, esize]<7:0>);
    if rounding then
        round_const = 1 << (-shift - 1); // 0 for left shift, 2^(n-1) for right shift 
    element = (Int(Elem[operand1, e, esize], unsigned) + round_const) << shift;
    if saturating then
        (Elem[result, e, esize], sat) = SatQ(element, esize, unsigned);
        if sat then FPSR.QC = '1';
    else
        Elem[result, e, esize] = element<esize-1:0>;

V[d] = result;