Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (scalar, B)

Test 1: uops

Code:

  sqabs b0, b0
  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)03080b18191e1f3a3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216112629100030383038303830383038
100430372300000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038
1004303722000078006125472510001000100039816013018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038
100430372200000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038
100430372200000006125472510001000100039816003018303730372414328951000100010003037303721100110000000000073116112629100030383038303830383038
100430372200000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038
1004303723000012006125472510001000100039816013018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038
1004303723000000061254725100010001000398160030183037303724143289510001000100030373037111001100000000048073116112629100030383038303830383038
100430372300000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038
100430372300000006125472510001000100039816013018303730372414328951000100010003037303711100110000000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs b0, b0
  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)03080b18191e1f3f4e51inst 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)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)9fa0a1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000870612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018302303003728264328745101002001000020010000300373003711102011009910010010000100200000071011611296330100001003003830038300383003830038
1020430037224000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000030071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100003000071011611296330100001003003830038300383003830038
10204300372250000007032954725101001001000010010000500427716030018300373022728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000030071011611296330100001003003830038300383003830038
10204300372250000210612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250084061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640516552962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640516562962910000103003830081300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640616662962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640616562962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640516552962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300842828632876710010201000020100003003730037111002110910101000010000640516562962910000103003830038300383003830038
10024300372250027061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640616642962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640616652962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000640616652962910000103003830038300383003830038
1002430037225000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010330640616652962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs b0, b8
  sqabs b1, b8
  sqabs b2, b8
  sqabs b3, b8
  sqabs b4, b8
  sqabs b5, b8
  sqabs b6, b8
  sqabs b7, b8
  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)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118216020036800001002004020040200402004020040
802042003915003152580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020114
80204201011500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500722580108100800081008002050064013202002020039200399977699908022220080032200801392003920039118020110099100100800001002131115118016120036800001002009920143200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000031115118016020036800001002004020040200402004020040
802042003915012302580108100800081008002050064013202002020039200939977699908012020080032200800322003920039118020110099100100800001000001115155016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a0b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000012004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000000050205164220036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000000050204164220036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002080213200392003911800211091010800001000000000050204164420036080000102004020040200402004020040
8002420039150000024004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000000050204164220036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020022200392003999963100198001020800002080000200392003911800211091010800001000000000050204164420036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000010000050203162420036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000000050204164220036080000102004020040200402004020040
800242003915000009004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000010000050204163420036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000000050204162420036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000000050204164420036080000102004020040200402004020040