Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (vector, integer, 4S from 4S)

Test 1: uops

Code:

  scvtf 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)03181e1f3f4e51inst 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
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110000973216332629100030383038303830383038
100430372200061254725100010001000398160030183037303724143289510001000100030373037111001100002173316332629100030383038303830383038
100430372300015625472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
10043037220001044254725100010001000398160030183037303724143289510001000100030373037111001100002473316332629100030383038303830383038
1004303723000842547251000100010003981600301830373037241432895100010001000303730371110011000010273316332629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000973316332629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100004573316332629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf 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)03081e3f4e51inst 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)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500147295472510100100100001001000050042771600300183003730037282716287401010020010008200100083003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282716287411010020010008200100083003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282716287401010020010008200100083003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282717287401010020010008200100083003730037111020110099100100100001000011171701600298550100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500145295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500919295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372240061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500145295472510100100100001001000050042771600300183003730037282753287451010020010000200100003003730037111020110099100100100001000000071011621296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000030191295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010306407166429678010000103003830038300383003830038
100253003722510000120103295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010306425168629629010000103003830038300383003830038
10024300372250000000166295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010306406165629629010000103003830038300383003830038
100243003722500000120233295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010306405165329631010000103003830038300383003830038
100243003722500000120187295472510010101000010100005042771603001830037300372828632876710012201000020100003003730037111002110910101000010000000306405165529629010000103003830038300383003830038
100243003722500000120235295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010306406166429629010000103003830038300383003830038
100243003722500000120166295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010306406166629629010000103003830038300383003830038
100243003722500000120187295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000050306406167629629010000103003830038300383003830038
100243003722500000120208295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000010006405166429629210000103003830038300383003830038
100243003722500000120254295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000306405165729629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf v0.4s, v8.4s
  scvtf v1.4s, v8.4s
  scvtf v2.4s, v8.4s
  scvtf v3.4s, v8.4s
  scvtf v4.4s, v8.4s
  scvtf v5.4s, v8.4s
  scvtf v6.4s, v8.4s
  scvtf 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)0307080a18191e1f3a3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150101000023725801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000111512281681020036800001002004020040200402004020040
8020420039150101000023725801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000111512281610520036800001002004020040200402004020040
80204200391501010000237258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000020711151228169920036800001002004020040200402004020040
802042003915010100002372580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151223163820036800001002004020040200402004020040
802042003915010100002372580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151229169920036800001002004020040200402004020040
8020420039150101000023725801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000111512210163920036800001002004020040200402004020040
802042003915010100002372580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151223168820036800001002004020040200402004020040
802042003915010100002372580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151228168820036800001002004020040200402004020040
802042003915010100002372580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151228168920036800001002004020040200402004020040
8020420039150101000023082580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151228168820036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115002782258001010800001080000506400000200200200392003999960310019800102080000208000020039200391180021109101080000101350201316552003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200203200392003999960310019800102080000208000020039200391180021109101080000100350201216452003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200200200392003999960310019800102080000208000020039200391180021109101080000100350205161062003680000102004020040200402004020040
800242003915000822580010108000010800005064000012002002003920039999603100198001020800002080000200392003911800211091010800001013502010164102003680000102004020040200402004020040
80024200391500082258001010800001080000506400000200200200392003999960310019800102080000208000020039200391180021109101080000101350201116382003680000102004020040200402004020040
80024200391500456125800101080000108000050640000120020020039200399996031001980010208000020800002003920039118002110910108000010105020516382003680000102004020040200402004020040
8002420039150051822580010108000010800005064000012002002003920039999603100198001020800002080000200392003911800211091010800001013502011161052003680000102004020040200402004020040
800242003915000705258001010800001080000506400000200200200392003999960310019800102080000208000020039200391180021109101080000101350209161162003680000102004020040200402004020040
800242003915001240258001010800001080000506400001200200200392003999960310019800102080000208000020039200391180021109101080000100350205161052003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020020039200399996031001980010208000020800002003920039118002110910108000010005020516652003680000102004020040200402004020040