Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTA (vector, 2S)

Test 1: uops

Code:

  frinta 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: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03191e3a3f4e51inst 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)a0acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724012085254725100010001000398160130183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
1004303723001138254725100010001000398160130183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
1004303723000170254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300082254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372403061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400061254725100010001000398160130183037303724143292010001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100003073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinta 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): 3.0037

retire (01)cycle (02)03080b0f18191e1f3a3f4e51inst 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)9fa0a1a6a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830083
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000735011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611297050100001003003830038300383003830038
1020430037233000000009529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
1020430037224000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003008530038300383003830038
1020430037224000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa0a6accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006403162229629010000103003830038300383003830038
10024300372240061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372330061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinta v0.2s, v8.2s
  frinta v1.2s, v8.2s
  frinta v2.2s, v8.2s
  frinta v3.2s, v8.2s
  frinta v4.2s, v8.2s
  frinta v5.2s, v8.2s
  frinta v6.2s, v8.2s
  frinta 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): 0.2505

retire (01)cycle (02)03191e1f3a3f51inst 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)9fa1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100002315011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000023011151180160020036800001002004020040200402004020040
802042003915501200302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000010011151180160020036800001002004020040200402004020040
80204201471550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000013011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000063011151180160020036800001002004020040200402004020040
80204200391610000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000010011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000043011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000112011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000540011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815503872580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020416442003680000102004020040200402004020040
800242003915503682580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020716472003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010035020516642003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010035020516542003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020416552003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020516672003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020516562003680000102004020040200402004020040
8002420039156012612580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020616552003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010105020516562003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020716452003680000102004020040200402004020040