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

SQDMULH (by element, H)

Test 1: uops

Code:

  sqdmulh h0, h0, v1.h[1]
  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 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)
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000
10043033100111000100075905100010000020001010000

Test 2: Latency 1->2

Code:

  sqdmulh h0, h0, v1.h[1]
  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)
1020430033101011011000010010000300768905101002001000620020010110000100
1020430033101011011000010010000300768905101002001000420020008110000100
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)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)
10024300331002121100002010000707689051002020100062020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000657691741005120100452020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010

Test 3: Latency 1->3

Code:

  sqdmulh h0, h1, v0.h[1]
  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)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)
10204300331010110110000010010000300768905101002001000620020012110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100
10204300331010110110000010010000300768905101002001000420020008110000100

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)
10024300331002121100002010000707689051002020100062020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010
10024300331002121100002010000707689051002020100002020000111000010

Test 4: throughput

Count: 8

Code:

  sqdmulh h0, h8, v9.h[1]
  sqdmulh h1, h8, v9.h[1]
  sqdmulh h2, h8, v9.h[1]
  sqdmulh h3, h8, v9.h[1]
  sqdmulh h4, h8, v9.h[1]
  sqdmulh h5, h8, v9.h[1]
  sqdmulh h6, h8, v9.h[1]
  sqdmulh h7, h8, v9.h[1]
  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)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)
80204400568010510180004100800080300032004480110200080014200160026180000100
80204400358010710180006100800100300032004480110200080014200160024180000100
80204400358010510180004100800080300032003680108200080012200160024180000100
80204400358010510180004100800080300032004480110200080013200160024180000100
80204400358010510180004100800080300032003680108200080012200160024180000100
80204400358010510180004100800080300032003680108200080012200160024180000100
80204401838020610180105100801090300032003680108200080012202160122280000100
80204400358010510180004100800080306032023280159202080061200160126180000100
80204400358010510180004100800080300032003680108200080012200160024180000100
80204400358010510180004100800080300032003680108200080012200160024180000100

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)
800244015680029218000820800126832000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010
800244007780027218000620800106832000080020208000020160000118000010
800244003580021218000020800006532000080020208000020160000118000010