Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT32Z (vector, 2D)

Test 1: uops

Code:

  frint32z 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)031e3f4e51inst 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)a0a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372496125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372408225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724126125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372466125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037242106125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037242316125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32z 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)03181e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295472510100100100001001000050042771603001830037300372827162874110100200100082001000830037300371110201100991001001000010045121117170160029646100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282716287411010020010008200100083003730037111020110099100100100001004601117180160029645100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160300183003730037282716287401010020010008200100083003730037111020110099100100100001004901117170160029646100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282717287401010020010008200101803003730037111020110099100100100001004401117170160029645100001003003830038300383003830038
1020430037225106129547251010010010000100100005004277160300183003730037282716287411010020010008200100083003730037111020110099100100100001004301117170160029645100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372827172874110100200100082001000830037300371110201100991001001000010049121117170160029645100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282716287411010020010008200100083003730037111020110099100100100001004001117180160029646100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282717287401010020010008200100083003730037111020110099100100100001003901117180160029646100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282716287411010020010008200100083003730037111020110099100100100001003831117180160029645100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160300183003730037282717287411010020010008200100083003730037111020110099100100100001003501117170160029645100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa0a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723303901032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037232000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372410001452954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
10024300372320007682954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010001000064021622296290010000103003830038300383003830038
1002430037233000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037233000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037232000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037233000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037233000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037233000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000064021622296290010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32z v0.2d, v8.2d
  frint32z v1.2d, v8.2d
  frint32z v2.2d, v8.2d
  frint32z v3.2d, v8.2d
  frint32z v4.2d, v8.2d
  frint32z v5.2d, v8.2d
  frint32z v6.2d, v8.2d
  frint32z 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)030418191e1f3a3f51inst 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)9fa0a1a6a7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915600000254258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100020000011151227399820036800001002004020040200402004020040
802042003915510000254258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151229169920036800001002004020040200402004020040
80204200391561000025425801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115122916101020036800001002004020040200402004020040
8020420039155100002542580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111512210169920036800001002004020040200402004020040
802042003916110060254258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151229529920036800001002004020040200402004020040
802042003915610000254258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100200003011151229169920036800001002004020040200402004020040
802042003915510000254258010810080008100800205006401320200202003920039997769990801202008003220080032200392025311802011009910010080000100000000011151229169420036800001002004020040200402004020040
802042003915510000254258010810080008100800205006409760200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151226166620036800001002004020040200402004020040
8020420039155100002646258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151229168820036800001002004020040200402004020040
80204200391561000025425801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000001115122816101020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)5f60696d6edispatch 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156094025803991080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100221415020716642003680000102004020040200402004020040
800242003915500402580010108000010800005064000011200202003920039999631001980010208000020800002003920039118002110910108000010000845020516562003680000102004020040200402004020040
8002420039155004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100001025020616652003680000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000245020616642003680000102004020040200402004020040
80024200391550040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616742003680000102019720103200402004020040
8002420039155004025800101080000108020950640000012002020039200399996310019800102080000208000020039200391180021109101080000100001145020616752003680000102004020040200402004020040
800242003915500110258030410800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000305020616742003680000102004020040200402004020040
80024200391560063025800101080000108000050640000002002020039200399996310019800102080210208000020039200391180021109101080000100001475020416462003680000102004020040200402004020040
8002420039156004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100001115020716642003680000102004020040200402004020040
8002420039155064025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100016285020516752003680000102014620093201022009620040