Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTP (scalar, D)

Test 1: uops

Code:

  frintp d0, d0
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110007073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
100430372496125472510001008100039816013018303730372414328951000100010003037303711100110000263073124112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112622100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintp d0, d0
  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)030918191e3f4e51inst 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)9fa0a1a3a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233010111612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
10204300372320000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000010000710011611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
102043003723201124612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000019000710011611296330100001003003830038300383003830038
1020430037233000123082954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000765111611296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500822954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010003006402162229629010000103003830038300383003830038
1002430037225001262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225001472954725100101010000101000050427716003001830037300372828672876710010201000020100003003730037111002110910101000010220206402162229629010000103003830038300843003830086
1002430084238106122954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500842954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225001032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintp d0, d8
  frintp d1, d8
  frintp d2, d8
  frintp d3, d8
  frintp d4, d8
  frintp d5, d8
  frintp d6, d8
  frintp d7, d8
  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)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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061155030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511831600200360800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001002534111513704800200360800001002009420102201152004020040
8020420226156030258010810080008100800205006401320200202034520039997769990801202008014320080141201652015631802011009910010080000100100111511801600200360800001002004020040200402004020040
8020420039155087258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039156030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100100111511801600200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100100111511801600200360800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001002600111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3f51inst 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)9fa8a9accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001010050207160662003680000102004020040200402004020040
80024200391560004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001010050206160662003680000102004020040200772004020040
8002420039160000117825800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001020350204160482003680000102004020040200402004020040
80024200391550006125800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001010350209160642003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001020350206160952003680000102004020040200402004020040
8002420039155000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000104300502061601152003680000102004020040200402004020040
80024200391550300402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000103035020111601052003680000102004020040200402004020040
8002420039156000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000103103502061604122003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050205160932003680000102004020040200402004020040
8002420039155000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101005020111605112003680000102004020040200402004020040