Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPS (vector, 4S)

Test 1: uops

Code:

  fcvtps v0.4s, v0.4s
  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)60696b6d6edispatch 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
10043037230103254725100010001000398160030180303730372414328951000100010003037303711100110000073116112626100030383038303830383038
10043037240103254725100010001000398160030180303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724061254725100010001000398160030180303730372414328951000100010003037303711100110002073116112629100030383038303830383038
10043037240612547251000100010003981600301803037303724143289510001000100030373037111001100010073116112699100030383038303830383038
1004303723061254725100010001000398160030180303730372414328951000100010003037303711100110000073216222626100030383038303830383038
1004303723061254725100010001000398160030180303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723061254725100010001000398160030180303730372413328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981600301803037303724143289510001000100030373037111001100011573216112629100030383038303830383038
10043037242461254725100010001000398160030180303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723361254725100010001000398160030180303730372413328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtps v0.4s, v0.4s
  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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330374295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001000071011611296330100001003003830038300383003830038
1020430037233961295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330210295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330156295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282716287411010020010008200100083003730037111020110099100100100001000311171701600296460100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300183003730037282716287411010020010008200100083003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300183003730037282717287411010020010008200100083003730037111020110099100100100001000011171801600296450100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300183003730037282716287411010020010008200100083003730037111020110099100100100001000011171801600296460100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003723200000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243008423300000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003723300000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716013001830037300702828632876710010201000020100003003730037111002110910101000010000640216332962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
1002430037225000002012954725100101010000101000050427716013001830037300372828632876710158201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtps v0.4s, v8.4s
  fcvtps v1.4s, v8.4s
  fcvtps v2.4s, v8.4s
  fcvtps v3.4s, v8.4s
  fcvtps v4.4s, v8.4s
  fcvtps v5.4s, v8.4s
  fcvtps v6.4s, v8.4s
  fcvtps v7.4s, v8.4s
  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)03091e3f51inst 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)9fa0a6a8acc2c5branch mispredict (cb)cdcfd5d6dde0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151182160200360800001002004020040200402004020040
8020420039155001382580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160200361800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181160200360800001002004020040200402004020040
8020420039161001382580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160200360800001002004020040200402004020040
802042003915600302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180161200360800001002004020040200402004020040
802042003915500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160200360800001002004020040200402004020040
802042003915500302580212100801121008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160200360800001002004020040200402004020040
802042003915600302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160200360800001002004020040200402004020040
802042003915500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160200360800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039518020110099100100800001000000211151180160200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e3f51inst 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)9fa0a6a8acbranch mispredict (cb)cdcfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015600000147258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502007161642003680000102004020040200402004020040
8002420039156000001452580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020016161632003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020013161652003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020016161652003680000102004020040200402004020040
800242003915500110822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020016161652003680000102004020040200402004020040
80024200391550000016625800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000024005020016166152003680000102004020040200402004020040
8002420039155000001452580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020016161632003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020016161662003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005037016166152003680000102004020040200402004020040
8002420039155000001482580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020016161642003680000102004020040200402004020040