Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FRINT32X (vector, 2D)

Test 1: uops

Code:

  frint32x v0.2d, v0.2d
  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: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03071e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723012061254725100010001000398160130183037303724143289510001000100030373037111001100000373216332629100030383038308530383038
100430372400061254725100010001000398160130183037303724143289510001000100030373037111001100020373316222629100030383038303830383038
1004303723000103254725100010001000398160130183037303724143289510001000100030373037111001100000073316322629100030383038303830383038
100430372400061254725100010001000398160130183037303724143289510001000100030373037111001100000373316222629100030383038303830383038
100430372400061254725100010001000398160130183037303724143289510001000100030373037111001100000073316332629100030383038308530383038
100430372400061254725100010001000398160130183037303724143289510001000100030373037111001100000073316332629100030383038303830383038
1004303723000210253825100010001000398160130183037303724136289510001000100030373037111001100000075416332629100030383038303830383038
100430372300061254725100010001000398160030183037303724143291410001000100030373037111001100000073316222629100030383038303830383038
100430372400061254725100010001000398160130183037303724143289510001000100030373037111001100000073316332629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000075316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32x v0.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5e60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320797295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233082295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011610296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600130018300373003728264328745101002001000020010000300373003711102011009910010010000100003071011611296330100001003003830038300383003830038
10204300372330726295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296331100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372330726295474410121100100001001000050042771600030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600130018300373003728264328745101002001000020010000300373003711102011009910010010000100010071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402166229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
100243003722500000001106295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006482162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32x v0.2d, v8.2d
  frint32x v1.2d, v8.2d
  frint32x v2.2d, v8.2d
  frint32x v3.2d, v8.2d
  frint32x v4.2d, v8.2d
  frint32x v5.2d, v8.2d
  frint32x v6.2d, v8.2d
  frint32x v7.2d, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8acc5branch mispredict (cb)cdcfd5d6e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815536302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
802042003915527682580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
802042003915542302580108100800081148002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
80204200391600302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
802042003915612302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
802042003915518302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
802042003915527302580108100800081008011650064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
80204200391560302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040
8020420039155121252580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016200360800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a8accdcficache miss (d3)d5d6d9ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015512061258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020012160121020036080000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000305020011160141520036080000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020012160141620036080000102004020040200402004020040
80024200391550040258001010800001080000506400000020069200392003999968100198001020800002080000200392003911800211091010800001000005020015390111520036080000102004020040200402004020040
80024200391551204025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502001416091120036080000102004020040200402004020040
80024200391553015225800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502001416011920036080000102004020040200402004020040
80024200391550040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020012160131120036080000102004020040200402004020040
800242003915527388272258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000015020015160161420036080000102004020040200402004020040
80024200391560040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020014160121220036080000102004020040200402004020040
80024200391550082258001010800971080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020013160181420036080000102004020040200402004020040