Specifications

Intel
®
Quark Core—Instruction Set Summary
Intel
®
Quark SoC X1000 Core
Developer’s Manual October 2013
288 Order Number: 329679-001US
FISUBR = Integer Subtract Reversed
ST(0)←16-bit memory-ST(0)
11011 110 : mod 101 r/m : s-i-b/disp. 24(20-35) 2 7(5-17)
ST(0)←32-bit memory-ST(0)
11011 010 : mod 101 r/m : s-i-b/disp. 22.5(19-32) 2 7(5-17)
FIMUL = Multiply Integer with ST(0)
ST(0)←ST(0) X 16-bit memory
11011 110 : mod 101 r/m : s-i-b/disp. 25(23-27) 2 8
ST(0)←ST(0) X 32-bit memory
11011 010 : mod 001 r/m : s-i-b/disp. 23.5(19-32) 2 8
FIDIV = Integer Divide
ST(0)←ST(0)/ 16-bit memory
11011 110 : mod 110 r/m : s-i-b/disp. 87(85-89) 2 70 3
ST(0)←ST(0)/ 32-bit memory
11011 010 : mod 110 r/m : s-i-b/disp. 85.5(84-86) 2 70 3
FIDVR = Integer Divide Reversed
ST(0)←16-bit memory/ST(0)
11011 110 : mod 111 r/m : s-i-b/disp. 87(85-89) 2 70 3
ST(0)←32-bit memory/ST(0)
11011 010 : mod 111 r/m : s-i-b/disp. 85.5(84-86) 2 70 3
FSQRT = Square Root
11011 001 : 1111 1010 85.5(83-87) 70
FSCALE = Scale ST(0) by ST(1)
11011 001 : 1111 1101 31(30-32) 2
FXTRACT = Extract Components of ST(0)
11011 001 : 1111 0100 19(16-20) 4(2-4)
FPREM = Partial Reminder
11011 001 : 1111 1000 84(70-138) 2(2-8)
FPREM1 = Partial Reminder (IEEE)
11011 001 : 1111 0101 94.5(72-167) 5.5(2-18)
FRNDINT = Round ST(0) to Integer
11011 001 : 1111 1100 29.1(21-30) 7.4(2-8)
Table 94. Floating-Point Clock Count Summary (Sheet 6 of 8)
Instruction Format
Cache Hit
Avg (Lower
Range...
Upper
Range)
Penalty
if
Cache
Miss
Concurrent
Execution
Avg (Lower
Range- Upper
Range)
Notes
Notes:
1. If operand is 0 clock counts = 27.
2. If operand is 0 clock counts = 28.
3. If CW.PC indicates 24 bit precision then subtract 38 clocks.
If CW.PC indicates 53 bit precision then subtract 11 clocks.
4. If there is a numeric error pending from a previous instruction, add 17 clocks.
5. If there is a numeric error pending from a previous instruction, add 18 clocks.
6. The INT pin is polled several times while this function is executing to ensure short interrupt latency.
7. If ABS(operand) is greater than π/4 then add n clocks, where n=(operand/(π/4)).