pldw
Preload Data for Write (A32)
PLDW [<Rn>, #<imm>]
Hints memory system to bring data into cache for writing.
Details
Preloads data for write by hinting the memory system to allocate cache line(s) in an exclusive state at the address computed from the base register and 12-bit immediate offset. This is a hint instruction and does not cause exceptions on address translation or access faults. Condition flags and general-purpose registers are unaffected. This instruction executes in A32 (ARM) instruction set only.
Pseudocode Operation
address = Rn + imm12
// Hint to memory system to preload for exclusive access (write)
PreloadDataForWrite(address)
Example
PLDW [r1, #16]
Encoding
Binary Layout
1111010
1
U
0
01
Rn
1
1
1
1
imm12
Operands
-
Rn
First source / base general-purpose register -
imm
Signed immediate value
Reference (Arm AArch32 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0xF510F000 | PLDW{<c>}{<q>} [<Rn> {, #{+/-}<imm>}] | A32 | 1111010 | 1 | U | 0 | 01 | Rn | 1 | 1 | 1 | 1 | imm12 | ||
| 0xF8B0F000 | PLDW{<c>}{<q>} [<Rn> {, #{+}<imm>}] | T32 | 111110001 | 0 | 1 | 1 | Rn | 1111 | imm12 | ||
| 0xF830FC00 | PLDW{<c>}{<q>} [<Rn> {, #-<imm>}] | T32 | 111110000 | 0 | 1 | 1 | Rn | 1111 | 1100 | imm8 | ||
| 0xF710F000 | PLDW{<c>}{<q>} [<Rn>, {+/-}<Rm> {, <shift> #<amount>}] | A32 | 1111011 | 1 | U | 0 | 01 | Rn | 1 | 1 | 1 | 1 | imm5 | stype | 0 | Rm | ||
| 0xF710F060 | PLDW{<c>}{<q>} [<Rn>, {+/-}<Rm> , RRX] | A32 | 1111011 | 1 | U | 0 | 01 | Rn | 1 | 1 | 1 | 1 | 00000 | 11 | 0 | Rm | ||
| 0xF830F000 | PLDW{<c>}{<q>} [<Rn>, {+}<Rm> {, LSL #<amount>}] | T32 | 111110000 | 0 | 1 | 1 | Rn | 1111 | 000000 | imm2 | Rm |
Description
Preload Data (immediate) signals the memory system that data memory accesses from a specified address are likely in the near future. The memory system can respond by taking actions that are expected to speed up the memory accesses when they do occur, such as preloading the cache line containing the specified address into the data cache.
The PLD instruction signals that the likely memory access is a read, and the PLDW instruction signals that it is a write.
The effect of a PLD or PLDW instruction is implementation defined. For more information, see Preloading caches.
Operation
if ConditionPassed() then
EncodingSpecificOperations();
address = if add then (R[n] + imm32) else (R[n] - imm32);
if is_pldw then
Hint_PreloadDataForWrite(address);
else
Hint_PreloadData(address);