Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPX (scalar, S)

Test 1: uops

Code:

  frecpx 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
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372206119002510001000100010445113018303730372738328951000100010003037303711100110004073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372206119002510001000100010445113018303730372738328951000100010003037303711100110001073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723126119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723061190025100010001000104451130183037303727383289510001000100030373037111001100012073116112919100030383038303830383038
100430372206119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000104210445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frecpx 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)031e1f3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250078919900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
1020430037225006619900251010010010000100100005001067451030018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
1020430037225008219900251010010010000100100005001067451130018300373003728588328776101592001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
10204300372250072619900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
10204300372250061519900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011621299190100001003003830038300383003830038
10204300372240012419900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000071011611299190100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162229919010000103003830038300383003830038
10024300372250017152319900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162229919010000103003830038300383003830038
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162229919010000103003830038300383003830038
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162629919010000103003830038300383003830038
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006403162229919010000103003830038300383003830038
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030075300371110021109101010000100026402162229919010000103003830038300383003830038
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162229919010000103003830038300383003830038
100243003722400025119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162229921010000103003830038300383003830038
10024300372250006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100006402162229990010000103003830038300383003830038
10024300372241006119900251001010100001010000501067451130090300373003728610328767100102010000201000030037300371110021109101010000100006402162229919010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frecpx s0, s8
  frecpx s1, s8
  frecpx s2, s8
  frecpx s3, s8
  frecpx s4, s8
  frecpx s5, s8
  frecpx s6, s8
  frecpx s7, s8
  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)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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020480040600639258010010080000100800005006400001800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151173160080036800001008004080040800408004080040
80204801375990392580100100800001008000050064000018002008003980039699710276999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
8020480039600039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
8020480039600039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800395990704258010010180000100800005256400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
80204800396000704258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151174161080036800001008004080040800408004080040
8020480039599039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
8020480039599039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
8020480039600039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170160080036800001008004080040800408004080040
8020480039600451058258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000011151170161080036800001008004080040800408004080040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308091e1f3f51inst 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)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)9fa8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6daddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800248092660711265215843828357804181080480108039050643451180020080039800396998637001980010208000020800008003980039118002110910108000010000502007081604280034080000108004080040800408004080086
8002480039600000053125800101080000108000050640000080020080039800396998637001980010208000020800008003980039118002110910108000010000502003051604380034080000108004080040800408004080040
800248013859900005025800101080000108000050640000080020080039800397001637001980010208000020800008003980039118002110910108000010000502004141604280034080000108004080040800408004080040
8002480039600006071525800101080000108000050640000080020080039800396998637001980010208000020800008003980039118002110910108000010000502000041604480034080000108004080040800408004080040
800248003959900005025800101080000108000050640000080020080039800396998637001980010208000020800008003980039118002110910108000010000502041041604280034080000108004080040800408004080040
8002480039600000019725800101080024108000050640000080020080039800396998637001980010208000020800008003980039118002110910108000010000502001041604280034080000108004080040800408004080040
800248003960000005025800101080000108000050640000080020080039800396998637001980010208000020800008003980039118002110910108000010000502001081603680034080000108004080040800408008980089
800248003959900005025800101080000108000050640000080020080039800396998637001980010208000020800008003980039118002110910108000010000502001071602480034080000108004080040800408004080040
8002480039600000050258001010800001080000506400000800200800398003969986370019800102080000208000080039800391180021109101080000100005020010416042800341580000108004080040800408004080040
800248003959900005025800101080000108000050640000080020080039800396998637001980038208000020800008003980039118002110910108000010001502000041604280034080000108004080040800408004080040