Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (scalar, integer, S from S)

Test 1: uops

Code:

  scvtf 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)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
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316112629100030383038303830383038
100430372396125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372208225472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722361254725100010001000398160130183037303724143289510001000100030373037111001100004873116112629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000112673116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf 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)03080b18191e1f3a3f4e51inst 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)9fa0a6a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000138295472510100100100001001000050042771601300183003730037282716287411010020010008204100083003730037111020110099100100100001000001011171701601296450100001003003830038300383003830038
1020430084225000051880103295472510100100100001001000050042771601300183003730037282716287411010020010008200100083008630037111020110099100100100001000001011171801600296460100001003003830038300383003830038
102043003722500001200166295472510100100100001001000050042771601300183003730037282643287451010020010165200100003003730037111020110099100100100001000001300071011611296330100001003003830038300383003830038
10204300372240000001170295472510100100100001001000050042771601300183003730037282643287581010020010000200100003003730037111020110099100100100001000001300071011611296330100001003003830038300383003830038
102043003722500001200103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000001300071011611296330100001003003830038300383003830038
10204300372250000000103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000300071011611296330100001003003830038300383003830038
10204300372250000120061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000300071011611296330100001003003830038300383003830038
10204300372250000120061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000011300071011611296330100001003003830038300383003830038
102043003722400001200189295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000001000071011611296330100001003003830038300383003830038
102043003722500001200103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000300071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e4f51inst 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
1002430037225000012001262954702510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010306404164329629010000103003830038300383003830038
1002430037225000012001242954702510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010006404164329629010000103003830038300383003830038
10024300372250000120012629547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037211002110910101000010000102306404164229629010000103003830038300383003830038
100243003722500000006129547025100101010000101000050427716003001830037300372828632876710010201000020101623003730037111002110910101000010000102479828304564329973110000103046630320305093051030516
1002430496229114101197880060132945709810094191008015115008842906800303783046330464283254328954115202011474261048430507302251111002110910101000010000022798308517967529953310000103046530461304603046630465
10024304582280110913208801674129547025100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010222021105607267337429629010000103003830038300383003830038
100243003722501866724400362829511025100101010000101000050427716003001830037300372828632876710164201000020114523017830275811002110910101000010000001407506403164429629010000103032230038303693037230226
10024304172260117118835203060295380185100651710000101000065427716003001830121304052830737288231091424113112010486304633022691100211091010100001002000306405244629629210000103003830134300383041830038
10024302632260084150005243295474622510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006404164329629010000103003830038300383003830038
100243003722500000004612954702510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006404163429629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf s0, s8
  scvtf s1, s8
  scvtf s2, s8
  scvtf s3, s8
  scvtf s4, s8
  scvtf s5, s8
  scvtf s6, s8
  scvtf s7, s8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491500000007625801081008000810080020500640132020108201122003999771510015802302008003220080032200392003911802011009910010080000100010311151181350020036800001002010020091200522009320040
802042003915000001202594580212100800121008012850064016402006120097201009987181001780228202801432008013720098200882180201100991001008000010030447511151360520020036800001002010220099200952010320091
8020420144150011116888321648021310080108100801325006409640200622003920039997769990801202008013820280142201092010121802011009910010080000100000011151180510020086800001002004020040200402004020040
80204200391501000120722580108100800081008002050064013202007320090200909987129990802322028013320080140200982009111802011009910010080000100010611151180160120036800001002004020040200402004020040
80204200391500000120156258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010611151180160020036800001002004020040200402004020040
8020420039150000030114258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000000093258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010311151180160020036800001002004020040200402004020040
8020420039150000012030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039150000012072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160020036800001002004020040200402004020040
8020420039150000012072258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010311151180160020036800001002004020040200402004020040

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)5f696d6edispatch 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502015166162003680000102004020040200402004020040
80024200391500822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050206166162003680000102004020040200402004020040
800242003915008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502016165132003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020161615162003680000102004020040200402004020040
800242003915008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502016161652003680000102004020040200402004020040
8002420039150154525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001010502016161462003680000102004020040200402004020040
800242003915001242580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050206161662003680000102004020040200402004020040
80024200391500837258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020161613162003680000102004020040200402004020040
8002420039150124025800101080000108000050640000020020200392003999963100198043320800002080000200392003911800211091010800001000502061613162003680000102004020040200402004020040
800242003915008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502016166162003680000102004020040200402004020040