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

CLS (vector, 2S)

Test 1: uops

Code:

  cls v0.2s, v0.2s
  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)
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000
1004203310011100010005024810001000100011000

Test 2: Latency 1->2

Code:

  cls v0.2s, v0.2s
  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)
1020520066101111031000810210034300509248101002001000620010006110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020520066101111031000810210034300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100
1020420033101011011000010010000300509248101002001000420010004110000100

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)
10024200331002121100002010000705092471002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010
10024200331002121100002010000705092481002020100002010000111000010

Test 3: throughput

Count: 8

Code:

  cls v0.2s, v8.2s
  cls v1.2s, v8.2s
  cls v2.2s, v8.2s
  cls v3.2s, v8.2s
  cls v4.2s, v8.2s
  cls v5.2s, v8.2s
  cls v6.2s, v8.2s
  cls v7.2s, v8.2s
  movi v8.16b, 9

(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)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)
802044006080107101800061008001003000320208801542000800642000800141080000100
802044003480107101800061008001003000320036801082000800122000800121080000100
802044004380105101800041008000803000320036801082000800122000800121080000100
802044003480105101800041008000803000320036801082000800122000801081080000100
802044003480105101800041008000803000320036801082000800122000800121080000100
802044003480105101800041008000803000320036801082000800122000800121080000100
802044003480105101800041008000803000320036801082000800122000800121080000100
802044003480105101800041008000803000320036801082000800122000801971080000100
802044003480105101800041008000803000320036801082000800122000800641080000100
802044003480107101800061008001003000320036801082000800122000800141080000100

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)
80024401958002721800062080010703200448003020800162080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010
80024400348002121800002080000703200008002020800002080000118000010