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, 8H)

Test 1: uops

Code:

  uminv h0, v0.8h
  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)03091e3a3f4e51inst 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
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073216112629100030383038303830383038
10043037220006125472510001000100039816003018303730372414328951000100020003037303711100110000373116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300033025472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200045125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200061254725100010001000398160130183037303724143289510001000200030373037111001100001873116112629100030383038303830383038
100430372200050925472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uminv h0, v0.8h
  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)9fa0a1a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722501662954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710021611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000104710011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
102043003722532352954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250612954725101271001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b1e1f3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640416222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030083300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100330640216222962910000103003830038300383003830038
10024300372250100078929547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100030640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250000072629547251001010100001010000504277160030018300843003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250000072629547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uminv h0, v8.8h
  uminv h1, v8.8h
  uminv h2, v8.8h
  uminv h3, v8.8h
  uminv h4, v8.8h
  uminv h5, v8.8h
  uminv h6, v8.8h
  uminv h7, v8.8h
  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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391501130258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151182161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010002311151181161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010001011151181481120036800001002004020040200402004020040
80204200391501130258010810080008100800205006409640200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915011695258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501130258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa8accfd2d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100350200416242003672080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200216242003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200416422003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050450416422003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200216242003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200416442003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200416422003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200216442003658080000102004020040200402004020040
800242003915007052580010108000010800005064000020020200392003999963100198001020800002016000020088200391180021109101080000101050200216442003658080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050200416432003658080000102004020040200402004020040