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

FRINT32Z (scalar, D)

Test 1: uops

Code:

  frint32z d0, d0
  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)
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000
1004303310011100010007590510001000100011000

Test 2: Latency 1->2

Code:

  frint32z d0, d0
  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)
1020430033101011011000010010000300768905101002001000620010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420210044210000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100
1020430033101011011000010010000300768905101002001000420010004110000100

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)
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010
10024300331002121100002010000707689051002020100002010000111000010

Test 3: throughput

Count: 8

Code:

  frint32z d0, d8
  frint32z d1, d8
  frint32z d2, d8
  frint32z d3, d8
  frint32z d4, d8
  frint32z d5, d8
  frint32z d6, d8
  frint32z d7, d8
  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 simd uop inputs (81)? int output thing (e9)? simd retires (ee)? int retires (ef)
8020440099801051018000410080008030003200368010820008001220080014180000100
8020440035801071018000610080010030003200368010820008001220080012180000100
8020440441802041018010310080107030003200368010820008001220080012180000100
8020440035801051018000410080008030003202088015420008006220080012180000100
8020440035801051018000410080008030003200368010820008001220080062180000100
8020440035801051018000410080008030003200368010820008001220080012180000100
8020440035801051018000410080008030003200368010820008001220080012180000100
8020440439802031018010210080106030003200448011020008001420080012180000100
8020440035801051018000410080008030003200368010820008001220080214180000100
8020440459802051018010410080108030003200368010820008001220080012180000100

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)
80024401918002921800082080012703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080067118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010
80024400358002121800002080000703200008002020800002080000118000010