Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPE (scalar, D)

Test 1: uops

Code:

  frecpe d0, d0
  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)031e3a3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372312266190025100010001000104451030183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
10043037230266190025100010001000104451130183037303727383289510001000100030373037111001100010376416442919100030383038303830383038
10043037230266190025100010001000104451030183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
10043037220266190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383085303830383038
10043037220266190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
10043037220266190025100010001000104451030183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
100430372218266190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
10043084220266190025100010001000104451130183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
10043037220266190025100010001000104451030183037303727383289510001000100030373037111001100000076416442919100030383038303830383038
10043037220266190025100010001000104451030183037303727383289510001000100030373037111001100000076416442919100030383038303830383038

Test 2: Latency 1->2

Code:

  frecpe d0, d0
  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)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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372240611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011610299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745130018300373003728588328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722502161199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250061199002510010101000010100005010674511300183003730075286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372240061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372240061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frecpe d0, d8
  frecpe d1, d8
  frecpe d2, d8
  frecpe d3, d8
  frecpe d4, d8
  frecpe d5, d8
  frecpe d6, d8
  frecpe d7, d8
  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)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)9fa8acc3c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204800396000171392580100100800001008000050064000018002080039800396997166999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800898004080040
8020480039599081692580100100800001008000250064001208002080039800396996596998080102200800142008001480039800391180201100991001008000010000022251271231180035800001008004080040800408004080040
8020480039599006926801001008000010080002500640012080020800398003969965106998180102200800142008001480039800391180201100991001008000010000022251281231180035800001008004080040800408004080040
802048003959900692680100100800001008000250064001218002080039800396996596998080102200800142008001480039800391180201100991001008000010000022251271171180035800001008004080089800408004080040
802048003959900692680100100800001008000250064001208002080039800396996596998180102200800142008001480039800391180201100991001008000010000022251281231180035800001008004080040800408004080040
802048003960000682680100100800001008000250064001208002080039800396996596998080102200800142008001480039800391180201100991001008000010000022251271231180035800001008004080040800408004080040
8020480039599066925801001008000010080002500640012080020800398003969965106998180102200800142008001480039800391180201100991001008000010000022251271231180035800001008004080040800408004080040
8020480039600006926801001008000010080002500640012080020800398003969965106998180102200800142008001480039800391180201100991001008000010000022251271231180035800001008004080040800408004080040
802048003960000682580100100800001008000250064001218002080039800396996596998180102200800142008001480039800391180201100991001008000010010022251281231180035800001008004080040800408004080040
80204800395990068258010010080000100800025006400121800208003980039699651069981801022008001420080014800398003911802011009910010080000100008001522251271231180035800001008004080040800408004080040

1000 unrolls and 10 iterations

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

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)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)9fa0a1a8a9acc2cfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024800406000502580010108000010800005064000008002008003980039699860370019800102080000208000080039800391180021109101080000100000005020171601668003480000108004080040800408004080040
8002480039600050258001010800001080000506400000800200800398003969986037001980010208000020800008003980039118002110910108000010000000502051601668003480000108004080040800408004080040
8002480039599050258001010800001080000506400000800200800398003969986037001980010208000020800008003980039118002110910108000010000000502061601668003480000108004080040800408004080040
8002480039600050258001010800001080000506400001800200800398003969986037001980010208000020800008003980039118002110910108000010000000502051605158003480000108004080040800408004080040
800248003960001064380010108000010800005064000018002008003980039699860370019800102080000208000080039800391180021109101080000100000005020161601668003480000108004080040800408004080040
80024800395990502580010108000010800005064000008002008003980039699860370019800102080000208000080039800391180021109101080000100000005020161601668003480000108004080040800408004080040
8002480039599050258001010800001080000506400001800200800398003969986037001980010208000020800008003980039118002110910108000010000000502061606168003480000108004080040800408004080040
800248003959905025800101080000108000050640000180020080039800396998603700198001020800002080000800398003911800211091010800001000000050201616016168003480000108004080040800408004080040
80024800396000502580010108000010800005064000018002008003980039699860370019800102080000208000080039800391180021109101080000100000005020161601368003480000108004080040800408004080040
80024800395990502580010108000010800005064000018002008003980039699860370019800102080000208000080039800391180021109101080000100000005020161601668003480000108004080040800408004080040