ldc1
Load doubleword to FP register pair
Loads the 64-bit value at the address in the second register plus an offset into the even FP register pair starting at the first.
Forms
ldc1 , ()
Pseudo-instructions
The processor does not have these forms. The assembler replaces each of them with one or more real instructions. Open a row to see them.
-
Read from label's address, reached through the %hi already in $t2
Set $f2 and $f3 register pair to 64-bit value at effective memory doubleword address
Operands
$f2- An even-numbered floating-point register,
$f0to$f30. A double-precision value uses this register and the next odd-numbered register. imm16- A signed 16-bit immediate,
-32768to32767. $t2- Any general-purpose register,
$0to$31, using its numeric or named spelling, such as$8or$t0($zerois$0;$rais$31). $f1- Any floating-point register,
$f0to$f31. label- A named address in the program, such as the start of a loop or a variable in
.data. imm- An immediate value: a signed 16-bit value (
-32768to32767) or a 32-bit value (-2147483648to4294967295). The size your value needs decides which real instructions the assembler uses. Open the row to see them for each size. imm32- A 32-bit immediate,
-2147483648to4294967295. A pseudo-instruction that takes one uses the register$atas a temporary, so$atloses the value it held.
Used to load a double-precision float from memory. Address must be doubleword-aligned and $f2 must be even-numbered.
.data
value: .double 3.5
.text
# Load the initialized value. Inspect $f2:$f3: double 3.5 (raw bits 0x400C000000000000).
la $t0, value
ldc1 $f2, 0($t0)