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

SUBHN (vector, 4S)

Test 1: uops

Code:

  subhn v0.4h, v0.4s, v1.4s
  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)
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000
1004303310011100010007590510001000200011000

Test 2: Latency 1->2

Code:

  subhn v0.4h, v0.4s, v1.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0033

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)
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300769247101312001004320020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100
1020430033101011011000010010000300768905101002001000420020008110000100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)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 simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
10024300331002121100002010000070076924710051200100442020000111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020010111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020000111000010
10024300331002121100002010000070076890510020200100002020000111000010

Test 3: Latency 1->3

Code:

  subhn v0.4h, v1.4s, v0.4s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0033

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)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 simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
1020430033101011011000010010000030007689051010020001000620020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100
1020430033101011011000010010000030007689051010020001000420020008110000100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

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)
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010

Test 4: throughput

Count: 8

Code:

  subhn v0.4h, v8.4s, v9.4s
  subhn v1.4h, v8.4s, v9.4s
  subhn v2.4h, v8.4s, v9.4s
  subhn v3.4h, v8.4s, v9.4s
  subhn v4.4h, v8.4s, v9.4s
  subhn v5.4h, v8.4s, v9.4s
  subhn v6.4h, v8.4s, v9.4s
  subhn v7.4h, v8.4s, v9.4s
  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)
80204400468010710180006100800103003200448011020080014200160028180000100
80204400358010710180006100800103003200368010820080012200160026180000100
80204400358010510180004100800083003200368010820080012200160026180000100
80204400358010510180004100800083003200368010820080012200160024180000100
80204400358010510180004100800083003200368010820080012200160024180000100
80204400358010510180004100800083003200368010820080012200160024180000100
80204400358010510180004100800083003200368010820080012200160024180000100
80204400358010510180004100800083003200368010820080012200160024180000100
80204400358010510180004100800083003200368010820080012200160024180000100
80204400358010510180004100800083003200368010820080012200160024180000100

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)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)
8002440203800292180008020800126832005280032208001820160000118000010
8002440038800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532016880065208005020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010
8002440035800212180000020800006532000080020208000020160000118000010