Apple M1 Microarchitecture Research by Dougall Johnson

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

ABS (vector, 2D)

Test 1: uops

Code:

  abs 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)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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300084254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372303161254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200061254725100010001000398160130223037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300082254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303723000103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  abs 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)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)9fa1a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000277507101161129669100001003003830038300383003830038
102043006122506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383022830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)60696b6d6edispatch 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000001562954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000055427716003001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000002322954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229691010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001803003730037282860328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  abs v0.2d, v8.2d
  abs v1.2d, v8.2d
  abs v2.2d, v8.2d
  abs v3.2d, v8.2d
  abs v4.2d, v8.2d
  abs v5.2d, v8.2d
  abs v6.2d, v8.2d
  abs 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)030b1e1f3f51inst 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)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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151182163320036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151183163420036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151184164520036800001002004020040200402004020040
8020420039150000512580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151183163420036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151183163420036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151183164320036800001002004020040200402004020040
80204200391500138176302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151184163420036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151183163420036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100000311151183163420036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151184164320036800001002004020040200402004020040

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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500084258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000502051666200361580000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050203163420036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001006050203166420036080000102004020040200402004020040
8002420039150004625800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001003150204164420036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001003050204166420036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001003050206166420036080000102004020040200402004020040
80024200391501204625800101080000108000050640000020020200392003999963100198001020800002080105201472003911800211091010800001010050207166420036080000102009320092200932009120040
800242003915000114425801081080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050204163420036080000102004020040200402004020040
800242003915090125625800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050206164720036080000102004020040200402004020040
8002420039150008225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050206166420036080000102004020040200402004020040