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

UADDL (vector, 8H)

Test 1: uops

Code:

  uaddl v0.8h, v0.8b, v1.8b
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.001

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000
1004203310011100010005024810001000200011000

Test 2: Latency 1->2

Code:

  uaddl v0.8h, v0.8b, v1.8b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0033

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
1020420033101011011000010010000300509248101002001000620020008110000100
1020420033101011011000010010000300509248101002001000620020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0033

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
10024200331002121100002010000705092471002020100062020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705095801005420100482020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705092481002020100002020000111000010
10024200331002121100002010000705092481002020100002020000111000010

Test 3: Latency 1->3

Code:

  uaddl v0.8h, v1.8b, v0.8b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0033

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
1020420033101011011000010010000300509248101002001000620020012110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020096110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100
1020420033101011011000010010000300509248101002001000420020008110000100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0033

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)int uops in schedulers (59)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
1486142663145152860100241631277610077705092481002020100042020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100042020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100002020000111000010
100242003310021211000002010000705092481002020100002020000111000010

Test 4: throughput

Count: 8

Code:

  uaddl v0.8h, v8.8b, v9.8b
  uaddl v1.8h, v8.8b, v9.8b
  uaddl v2.8h, v8.8b, v9.8b
  uaddl v3.8h, v8.8b, v9.8b
  uaddl v4.8h, v8.8b, v9.8b
  uaddl v5.8h, v8.8b, v9.8b
  uaddl v6.8h, v8.8b, v9.8b
  uaddl v7.8h, v8.8b, v9.8b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5004

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
80204400578010610180005100800093003200448011020080014200160028180000100
80204400348010710180006100800103003200368010820080012200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100
80205400698014310380040102800523003202048015320080063200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100
80204400348010510180004100800083003200368010820080012200160024180000100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5004

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
800244009780029218000820800126832000080020208000020160000118000010
800244003480021218000020800006532000080020208000020160000118000010
800254006980063218004220800546532000080020208000020160000118000010
800244003480021218000020800006932000080020208000020160000118000010
800254006980056218003520800436532000080020208000020160000118000010
800244003480021218000020800006532000080020208000020160000118000010
800244003480021218000020800006532005280032208001720160000118000010
800244003680021218000020800006532000080020208000020160000118000010
800244003480021218000020800006532000080020208000020160000118000010
800244003480021218000020800006532000080020208000020160000118000010