Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

LD3R (post-index, 4S)

Test 1: uops

Code:

  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop
  mov x0, 1
  mov x1, 2
  mov x8, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires (minus 60 nops): 4.000

Issues: 5.006

Integer unit issues: 1.001

Load/store unit issues: 1.000

SIMD/FP unit issues: 3.006

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)dispatch uop (78)map ldst uop (7d)map simd uop (7e)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)
64005298775087100730741006100630181000300030002305150001000300020003000100110003000
64004295585007100130061000100030001000300030002305150001000300020003000100110003000
64004295445007100130061000100030001000300030002305150001000300020003000100110003000
64004295495007100130061000100030001000300030002305150001000300020003000100110003000
64004295405007100130061000100030001000300030002305150001000300020003000100110003000
64004299975007100130061000100030001000300030062306950001000300020003000100110003000
64004299675007100130061000100030001000300030002305150001000300020003000100110003000
64004295495007100130061000100030001000300030002305150001000300020003000100110003000
64004295435007100130061000100030001000300030002305150001000300020003000100110003000
64004295625007100130061000100030001000300030002305150001000300020003000100110003000

Test 2: throughput

Count: 8

Code:

  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  ld3r { v0.4s, v1.4s, v2.4s }, [x6], x8
  mov x7, x6
  mov x8, x6
  mov x9, x6
  mov x10, x6
  mov x11, x6
  mov x12, x6
  mov x13, x6
  mov x8, 0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.5006

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
320206120199400289801352401208003480136240100800242403692400721701868400214200800252400752001600102400158000480000240000100
320204120056400126801042400198000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600522400788002580000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600102400158000480000240000100
320204120048400122801042400158000380104240010800042403122400152400284400118200800052400152001600522400788002580000240000100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.5007

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
320025120156400107800242400708001380024240036800002400302400032400430400010208000024000020160052240078800258000024000010
320024120060400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160042240063800228000024000010
320024120096400046800112400358000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010
320024120054400033800112400228000080010240000800002400302400032400378400010208000024000020160000240000800018000024000010