Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPE (vector, 2S)

Test 1: uops

Code:

  frecpe v0.2s, v0.2s
  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)03070a1e3a3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723110268190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
1004303723110268190025100010001000104451130183037303727383289510001000100030373037111001100000376416442919100030383038303830383038
1004303723110268190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
1004303722110289190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
1004303723110268190025100010001000104451030183037303727383289510001000100030373037111001100006076416442919100030383038303830383038
1004303723110268190025100010001000104451130183037303727383289510001000100030373037111001100007376416442919100030383038303830383038
10043037221102681900251000100010001044510301830373037273832895100010001000303730371110011000006676416442919100030383038303830383038
1004303723110268190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
1004303723110268190025100010001000104451030183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
1004303723110268190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038

Test 2: Latency 1->2

Code:

  frecpe v0.2s, v0.2s
  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)030b18191e1f3f4e51inst 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)6061696b6d6edispatch 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)9fa8a9acc5cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000014519900251010010010000100100005001067451103001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
1020430037225000006119900251010010010000100100005001067451103001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
10204300372250000035319900251010010010000100100005001067451003001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299198100001003003830038300383003830038
1020430131224003006119900251010010010000100100005001067451003001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
1020430037225000006119900251010010010000100100005001067451103001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
102043003722500000420199002510100100100001001000050010674510030018030037300372858832874510100200100002001000030037300371110201100991001001000010000570710011611299190100001003003830038300853003830038
10204300372250000027219900251010010010000100100005001067451003001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
1020430037225000006119900251010010010000100100005001067451003001803003730037285883287791010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
10204300372250000026119900251010010010000100100005001067451003001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038
1020430037225000006119900251010010010000100100005001067451103001803003730037285883287451010020010000200100003003730037111020110099100100100001000000710011611299190100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b18191e1f3a3f4e51inst 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
10024300372250000000061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000000006405166629919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006406166629919010000103008530038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006407167629919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006406166729919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000306406166729919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006407167629919010000103003830038300383003830038
10024300372250000000061199002510010101000710100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006407167729919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006406167729919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006406167629919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006407167729919010000103003830228300383003830038

Test 3: throughput

Count: 8

Code:

  frecpe v0.2s, v8.2s
  frecpe v1.2s, v8.2s
  frecpe v2.2s, v8.2s
  frecpe v3.2s, v8.2s
  frecpe v4.2s, v8.2s
  frecpe v5.2s, v8.2s
  frecpe v6.2s, v8.2s
  frecpe v7.2s, v8.2s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)0308090b191e1f3a3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204800406000000878803052580100100800001008000050064000008002080039800396997166999380100200800082008000880039800391180201100991001008000010000010001115117116080036800001008004080040800408004080040
8020480039600000027300602580100100800001008000050064000008002080039800396997166999380100200800082008000880039800391180201100991001008000010022000001115117016080036800001008004080040800408004080040
8020480039600000032400392580100100800001008000050064000008002080039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080036800001008004080040800408004080040
8020480039600000387000392580100100800001008000050064000018024880039800396997166999380100200800082008005580087800393180202100991001008000010000000001115117116080036800001008004080040800408004080040
8020480039600000029700392580100100800001008000050064000018002080039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080036800001008004080040800408004080040
8020480039599000046500392580100100800001008000050064000018002080039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080036800001008004080040800408004080040
8020480039600000035100392580100100800001008000050064000018010780039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080085800001008004080040800408004080089
8020480039600000062700392580100100800001008000050064000018002080039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080036800001008004080040800408004080040
802048003959900003481760392580100100800001008000050064000008002080039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080036800001008004080040800408004080040
8020480039599000075600392580100100800001008000050064000008002080039800396997166999380100200800082008000880039800391180201100991001008000010000000001115117016080036800001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa0a1a6a8acc2cdcfd2d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002480040600000008122580010108000010800005064000008002080039800396998603700198001020800002080000800398003911800211091010800001000069000502003160348003480000108004080040800408004080040
8002480039599000005025800101080000108000050640000080020800398003969986037001980010208000020800008003980039118002110910108000010000771200502004160348003480000108004080040800408004080040
8002480039600000007152580010108000010800005064000008002080039800396998603700198001020800002080041800398003911800211091010800001000076000502004160348003480000108004080040800408004080040
800248003959900012050258001010800001080026506400000800208003980039699860370019800102080000208000080039800391180021109101080000100001000502003160448003480000108004080040800408004080040
80024800395990000050258001010800001080000506400000800208003980039699860370019800102080000208000080039800391180021109101080000100004000502004160448003480000108004080040800408004080040
80024800395990000050258001010801201080000506400000800208003980039699860370019800102080000208000080039800391180021109101080000100000000502004160358003480000108004080040800408004080040
80024800396000000050258003510800001080000556400001800698003980039699860370019800362080000208000080039800391180021109101080000100000000502004160538003480000108004080040800408004080040
80024800396000000050258001010800001080000506400000800208003980039700060370019800102080000208000080039800391180021109101080000100000000502004160438003480000108004080236800908004080040
80024800395991000014652580010108000010800005064000018002080039800396998603700198001020800002080000800398003911800211091010800001000003320502004160448003580000108004080040800408004080040
80024800395990203030798258001010800001080000506400001800208003980039699860370019800102080000208000080039800391180021109101080000100000000504603320448022680000108004080040800408004080040