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, 4H)

Test 1: uops

Code:

  uminv h0, v0.4h
  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)03181e1f3f4e51inst 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
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372302406125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372305706125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200025125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300013625472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uminv h0, v0.4h
  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)0308090b1e3f4e51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000726295472510100100100001001000050042771601300180300373003728264328745101002001000020020000300373003711102011009910010010000100002071011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000033371011611296330100001003003830038300383003830038
10204300372250000726295472510100100100001001000050042771600300180300373003728264328745101002001000020020000300373003711102011009910010010000100002671011611296330100001003003830038300383003830038
102043003722500005362954725101001001000010010000500427716003001803003730037282643287451010020010000200200003003730037111020110099100100100001000020710116112966822100001003003830038300383003830038
1020430037225111061295292510100100100001001000050042771600300180300373003728264328745101002001000020020000300373003721102011009910010010000100000071011611296330100001003003830086301323008630038
10204300372250000103295472510100100100001001000050042771600300180300373003728264328745101002001000020020000300373003711102011009910010010000100001371011611296330100001003003830038300383003830038
10204300372250001261295472510100100100001001000050042771600300180300373003728264328745101002001000020020000300373003711102011009910010010000100001071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018030037300372826432874510100200100002002000030037300371110201100991001001000010000010571011611296330100001003003830038300383003830038
1020430037225000094295472510100100100001001000050042771600300180300373003728264328745101002001000020020000300373003711102011009910010010000100003071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300180300373003728264328745101002001000020020000300373003711102011009910010010000100001071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)9fa1a6a7a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001210000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010001328190640216222962910000103003830038300383003830038
100243003722406129547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000201640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000100640216222962910000103003830038300383003830038
100243003722406129547251001010100001010000504277160130018030037300372828632876710010201000020200003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018330037300372828632876710010201000020200003003730037111002110910101000010000130640216222962910000103003830038300383003830038
1002430037225072629547251001010100001010000504277160030018030037300372828632876710010201000020200003003730037111002110910101000010000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uminv h0, v8.4h
  uminv h1, v8.4h
  uminv h2, v8.4h
  uminv h3, v8.4h
  uminv h4, v8.4h
  uminv h5, v8.4h
  uminv h6, v8.4h
  uminv h7, v8.4h
  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)03090b1e3a3f51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151184163320036800001002004020040200402004020040
80204200391500000315258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151184164320036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151184163420036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151184164320036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000309011151184163420036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000100011151183163420036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010000000211151184164320036800001002004020040200402004020040
8020420039150006030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010020103011151182163420036800001002004020040200402004020040
8020420039150004206622580108100803051008002050064013212002020039200889977269990801202008003220016006420039200391180201100991001008000010000509011151184163420083800001002004020040200402004020040
8020420039150000093258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010002100011151183164320036800001002004020040200402004020040

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)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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010022050207161242003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020516842003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010001350204161272003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416492003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005045316952003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010001350201016532003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416552003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020516452003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050205165112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020816562003680000102004020040200402004020040