vldr
Vector Load Register (VFP)
VLDR<c> <Sd>, [<Rn>, #+/-<imm>]
Loads a floating-point register from memory.
Details
Loads a single-precision floating-point value from memory into a VFP register using a PC-relative or register-relative address with an optional offset. The memory access uses the address [Rn ± (imm8 << 2)]. Executed in A32/T32 with VFP extension; no condition flags are affected.
Pseudocode Operation
offset ← ZeroExtend(imm8) << 2
if U == 1 then
address ← Rn + offset
else
address ← Rn - offset
Sd ← [address]
Example
VLDR s0, [r1, #+/-#16]
Encoding
Binary Layout
cond
110
1
U
D
0
1
Rn
Vd
10
10
imm8
Operands
-
Sd
Destination 32-bit floating-point register -
Rn
First source / base general-purpose register -
imm
Signed immediate value
Reference (Arm AArch32 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0x0D100900 | VLDR{<c>}{<q>}.16 <Sd>, [<Rn> {, #{+/-}<imm>}] | A32 | cond | 110 | 1 | U | D | 0 | 1 | Rn | Vd | 10 | 01 | imm8 | ||
| 0x0D100A00 | VLDR{<c>}{<q>}{.32} <Sd>, [<Rn> {, #{+/-}<imm>}] | A32 | cond | 110 | 1 | U | D | 0 | 1 | Rn | Vd | 10 | 10 | imm8 | ||
| 0x0D100B00 | VLDR{<c>}{<q>}{.64} <Dd>, [<Rn> {, #{+/-}<imm>}] | A32 | cond | 110 | 1 | U | D | 0 | 1 | Rn | Vd | 10 | 11 | imm8 | ||
| 0xED100900 | VLDR{<c>}{<q>}.16 <Sd>, [<Rn> {, #{+/-}<imm>}] | T32 | 1110110 | 1 | U | D | 0 | 1 | Rn | Vd | 10 | 01 | imm8 | ||
| 0xED100A00 | VLDR{<c>}{<q>}{.32} <Sd>, [<Rn> {, #{+/-}<imm>}] | T32 | 1110110 | 1 | U | D | 0 | 1 | Rn | Vd | 10 | 10 | imm8 | ||
| 0xED100B00 | VLDR{<c>}{<q>}{.64} <Dd>, [<Rn> {, #{+/-}<imm>}] | T32 | 1110110 | 1 | U | D | 0 | 1 | Rn | Vd | 10 | 11 | imm8 | ||
| 0x0D1F0900 | VLDR{<c>}{<q>}.16 <Sd>, <label> | A32 | cond | 110 | 1 | U | D | 0 | 1 | 1111 | Vd | 10 | 01 | imm8 | ||
| 0x0D1F0A00 | VLDR{<c>}{<q>}{.32} <Sd>, <label> | A32 | cond | 110 | 1 | U | D | 0 | 1 | 1111 | Vd | 10 | 10 | imm8 | ||
| 0x0D1F0B00 | VLDR{<c>}{<q>}{.64} <Dd>, <label> | A32 | cond | 110 | 1 | U | D | 0 | 1 | 1111 | Vd | 10 | 11 | imm8 | ||
| 0xED1F0900 | VLDR{<c>}{<q>}.16 <Sd>, <label> | T32 | 1110110 | 1 | U | D | 0 | 1 | 1111 | Vd | 10 | 01 | imm8 | ||
| 0xED1F0A00 | VLDR{<c>}{<q>}{.32} <Sd>, <label> | T32 | 1110110 | 1 | U | D | 0 | 1 | 1111 | Vd | 10 | 10 | imm8 | ||
| 0xED1F0B00 | VLDR{<c>}{<q>}{.64} <Dd>, <label> | T32 | 1110110 | 1 | U | D | 0 | 1 | 1111 | Vd | 10 | 11 | imm8 |
Description
Load SIMD&FP register (immediate) loads a single register from the Advanced SIMD and floating-point register file, using an address from a general-purpose register, with an optional offset.
Depending on settings in the CPACR, NSACR, HCPTR, and FPEXC registers, and the Security state and PE mode in which the instruction is executed, an attempt to execute the instruction might be undefined, or trapped to Hyp mode. For more information, see Enabling Advanced SIMD and floating-point support.
Operation
if ConditionPassed() then
EncodingSpecificOperations();
CheckVFPEnabled(TRUE);
base = if n == 15 then Align(PC,4) else R[n];
address = if add then (base + imm32) else (base - imm32);
case esize of
when 16
S[d] = Zeros(16) : MemA[address,2];
when 32
S[d] = MemA[address,4];
when 64
word1 = MemA[address,4];
word2 = MemA[address+4,4];
// Combine the word-aligned words in the correct order for current endianness.
D[d] = if BigEndian(AccessType_ASIMD) then word1:word2 else word2:word1;