Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMS (vector, 4H)

Test 1: uops

Code:

  fcvtms v0.4h, 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)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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
10043037231222025472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110001275573116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308425472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724022025472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724059925472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms v0.4h, 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)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)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)9fa0a1a6a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723318196295472510100100100001001000050042771601300183003730037282717287401010020010008200100083003730037111020110099100100100001000000000111718016002964500100001003003830038300383003830038
1020430037232914529547251010010010000100100005004277160030018300373003728271728741101002001000820010008300373003711102011009910010010000100262000000000710116112963300100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
10204300372330726295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
10204300372321261295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000000710116112963300100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771601300183003730037282716287401010020010008200100083003730037111020110099100100100001000000000111718016002964600100001003003830038300383003830038

1000 unrolls and 10 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)72scheduler 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)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037232000008229547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403167329629010000103003830038300383003830038
10024300372330000037229547251001010100081010000604277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037232000006129547251001212100001010000604277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037243000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403165329629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830086300853003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329631210000103003830038300383003830038
1002430037224000006129547251001010100001210000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010006404163329629010000103003830038300383003830038
1002430037224000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010006425163329629010000103003830038300383003830038
1002430037225000006129547251001210100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms v0.4h, v8.4h
  fcvtms v1.4h, v8.4h
  fcvtms v2.4h, v8.4h
  fcvtms v3.4h, v8.4h
  fcvtms v4.4h, v8.4h
  fcvtms v5.4h, v8.4h
  fcvtms v6.4h, v8.4h
  fcvtms v7.4h, 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)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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391560302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180190020036800001002004020040200402004020040
802042003915615302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039418020110099100100800001000000011151180760020036800001002004020040200402004020040
80204200391560302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915505052580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080352200800322003920039118020110099100100800001000000011151180160020099800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000311151180160020036800001002004020040200402004020040

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)9faccfd0d5d6ddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050209116112003600080000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100502001298141212003600080000102004020040200402004020040
8002520039156040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040
80024200391561240258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010350200116112003600080000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040
8002420039156040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010050200116112003600080000102004020040200402004020040