Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNU (vector, 2D)

Test 1: uops

Code:

  fcvtnu 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)03181e3f4e51inst 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
1004303723096125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723008225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301986125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723036125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724066125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230246125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtnu 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)0318191e1f3a3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003724100000234295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000093741202430164400100001003075530553307053069830656
1020430706246141418481144190112942829110266151100241001015079142894531300183003730085283126928980121162361231624012321307023056111110201100991001001000010000710216222963300100001003003830038300383003830038
1020430037233000001682954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216222963300100001003003830038300383003830038
1020430037233000004632954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216222963300100001003003830038300383003830038
10204300372330012001662954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216222963300100001003003830038300383003830038
10204300372320000022002954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216222963300100001003003830038300383003830038
1020430037233000004292954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216222963300100001003003830038300383003830038
1020430037233000004072954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010003710216222963300100001003003830038300383003830038
10204300372330012009262954725101001001000010010000500427716013001830037300372826432874510100200100002001018030037300371110201100991001001000010000710216222963300100001003003830038300383003830038
1020430037233000001452954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216222963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3f4e51inst 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)9fa0a1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000000000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006404162229629010000103003830038300383003830038
1002430037233000000000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000002642954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000000822954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629410000103027430415302283041530180
1002430213228200118354601032954749100191310008101015050428256803009003008430085282887288051016220103312010166301323008421100211091010100001002243206402242229629010000103008530038300383008530038
1002430037225000000000337329484118100871210064171090087427716003001803003730037282863287671001020101612010000300373013211100211091010100001042142833006814162229629010000103003830038300383013230038
10024300842250110000278814572954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000000090612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtnu v0.2d, v8.2d
  fcvtnu v1.2d, v8.2d
  fcvtnu v2.2d, v8.2d
  fcvtnu v3.2d, v8.2d
  fcvtnu v4.2d, v8.2d
  fcvtnu v5.2d, v8.2d
  fcvtnu v6.2d, v8.2d
  fcvtnu 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)0307080a1e3a3f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048155101018225801081008000810080020500640132020106201032003999876999080120200800322008003220039200391180201100991001008000010020011151181161120036800001002004020040200402004020040
80204200391551011203025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039155101003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039155101007225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000311151181161420036800001002004020040200402004020040
8020420039155101003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391551010077625801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151381161120036800001002004020040200402009420040
802042003915501012011425801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000311151181161120036800001002004020040200402004020040
8020420039156000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001011151181161120036800001002004020040200402004020040
8020420039156000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039155000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010005011151181162120036800001002004020040200402004020040

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)9fa8a9accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501559402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001010050202316232003680000102004020040200402004020040
80024200391560402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050201316332003680000102004020040200402004020040
80024200391550402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200316322003680000102004020040200402004020040
80024200391610402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001010050200216322003680000102004020040200402004020040
80024200391550402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200316332003680000102004020040200402004020040
80024200391550822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200216332003680000102004020040200402004020040
80024200391550402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200316232003680000102004020040200402004020040
800242003915512402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200316332003680000102004020040200402004020040
80024200391550402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000350200316332003680000102004020040200402004020040
80024200391560402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200316232003680000102004020040200402004020040