Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNMV (4S)

Test 1: uops

Code:

  fminnmv s0, v0.4s
  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: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03191e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100030073116112629100030383038303830383038
10043037230961254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723012126254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100010073116112629100030383038303830383038
10043037220061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722021384254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fminnmv s0, 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): 3.0037

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)60696b6d6edispatch 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)9faccdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372252761295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100017101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)60696b6d6edispatch 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100020006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372240000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fminnmv s0, v8.4s
  fminnmv s1, v8.4s
  fminnmv s2, v8.4s
  fminnmv s3, v8.4s
  fminnmv s4, v8.4s
  fminnmv s5, v8.4s
  fminnmv s6, v8.4s
  fminnmv s7, v8.4s
  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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611510512580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511821622200360800001002004020040200402004020040
80204200391500512580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511821621200361800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000099111511811612200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511821622200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000003111511821621200360800001002004020040200402004020040
8020420039150123025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000033111511821621200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511811612200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511821622200360800001002004020040200402004020040
8020420039150030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000114111511811621200360800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511821622200360800001002009920040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)696d6edispatch stall (70)72scheduler 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)9fa7a8a9accfd0d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001003301715020041644200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001000005020041624200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001000005020041634200360080000102004020040200402004020040
80024200391500084778001010800001080000506400002002020039200399996031001980010208000020800002003920039118002110910108000010000605020041634200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001000005020021634200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001000005020041624200360080000102004020040200402004020040
80024200391500040258001010800001080000506400002002020039200399996031001980010208000020800002003920039118002110910108000010033035020031642200360080000102004020040200402004020040
8002420088150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001000005020021644200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001008035020041624200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999603100198001020800002080000200392003911800211091010800001000005020041624200360080000102004020040200402004020040