Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64X (scalar, S)

Test 1: uops

Code:

  frint64x s0, s0
  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)030b1e3f4e51inst 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)a0a1a6a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220072425472510001000100039816013018303730372414729071000100010003037303711100110000000373116112629100030383038308630383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110001000373116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64x s0, s0
  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)0308090a0b18191e1f3a3f4e51inst 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)inst ldst (9b)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042775541300183003730037282643287451010020010000200100003003730037111020110099100100100000100000100071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722400000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
1020430037225000000000103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038
102043003722500000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100000100000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000021061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006406163329629010000103003830038300383003830038
10024300372330000273062295472510010101000010100005042771601300183003730037282883287671001020100002010000301313008441100211091010100001000000006403163329629010000103003830038300383003830038
10024300372320000195061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003723300000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372330000390061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
10024300372320000330103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000200006403163329629010000103003830038300383003830038
100243003723300300061295472510010101000010100006042771600300183003730037282863288431001020100002010000301793017841100211091010100001000210843306403163329629010000103003830038300383017930178
10024302722341123004265295292510010101000012100006642812161301983003730037283013287671001022100002010000300373013211100211091010100001000000007033403429736210000103003830038300383007430038
1002430037232000018002108295474310010101000017106006042771601300183003730180282863287671046220100002010331300373003711100211091010100001000000016403164529776310000103008630038300383008530086
100243003723310000026822954780100101010000141015065427716013001830037300372828632876710913221131922100003013130037111002110910101000010202102782008484975429989410000103055630511305073055930514

Test 3: throughput

Count: 8

Code:

  frint64x s0, s8
  frint64x s1, s8
  frint64x s2, s8
  frint64x s3, s8
  frint64x s4, s8
  frint64x s5, s8
  frint64x s6, s8
  frint64x s7, s8
  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)03080918191e3f51inst 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)5e60696d6edispatch 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)9fa0a8acb1c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581550000061258010810080008100800205006401320120020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118011600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013201200202003920039997769990801202008003220080032200392003911802011009910010080000100008401115118001600200361800001002004020040200402004020040
8020420039155000003025801081008000810080020500640132002002020039200399977699908012020080032200800322003920039118020110099100100800001000010201115118001600200360800001002004020040200402004020040
802042003915500000302580108100800081008002050064013200200202003920039997769990801202008003220080032200392003911802011009910010080000100007801115118001600200360800001002004020040200402004020040
8020420039155000003025801081008000810080020500640132002002020039200399977699908012020080032200800322003920039118020110099100100800001000022501115118001600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118001600200360800001002004020040200402004020040
80204200391550000072258010810480406100800205006425760020020200902014199776999080120200800322008003220039200391180201100991001008000010000901115118001600200360800001002004020040200402004020040
80204200391560000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118001600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118001600200360800001002004020040200902004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000301115118001600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040a0b181e3f51inst 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)9fa6a8a9accfd2d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501550000061258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020410160372003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100100502007160442003680000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020410160732003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502003160372003680000102004020040200402004020040
800242003915500000610120803041080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502003160332003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000502003160332003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000002002020039200399996310029800102080000208000020039200391180021109101080000100000502007160732003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502003160332003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502003160472003680000102004020040200402004020040
8002420039155001004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502003160332003680000102004020040200402004020040