Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINV (vector, 8B)

Test 1: uops

Code:

  uminv b0, v0.8b
  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)0308091e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013054303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300816125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200010325472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uminv b0, v0.8b
  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)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)9fa0a1a6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000171011611296332100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372240034629547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011621296330100001003003830038300383003830038
10204300372250076229547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830085300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300372110021109101010000100640216222962910000103003830038300383003830038
100243003722501956129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037224006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830083
1002430037225008229547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640241222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uminv b0, v8.8b
  uminv b1, v8.8b
  uminv b2, v8.8b
  uminv b3, v8.8b
  uminv b4, v8.8b
  uminv b5, v8.8b
  uminv b6, v8.8b
  uminv b7, v8.8b
  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)03070a3f51inst 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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150115052580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003914911302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181162120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040
802042003915011302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100011151181161120036800001002004020040200402004020040

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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115600705258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020316212003680000102004020040200402004020040
80024200391500082258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020216322003680000102004020040200402004020040
800242003915000103258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116122003680000102004020040200402004020040
800242003915000211258001010800001080000506400001200200200392003999963100198001020800002016000020039200891180021109101080000100005020116122003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040