Apple M1 Microarchitecture Research by Dougall Johnson

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

FRSQRTE (scalar, S)

Test 1: uops

Code:

  frsqrte 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)03083f4e51inst 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
100430372206119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510081000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372209419002510001000100010445103018303730372738328951000100010003037303711100110000073124112919100030383038303830383038
100430372306119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723025119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372208419002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372206119002510001000100010445103018303730372738328951000100010003037303711100110000073116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frsqrte 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
1020430037224000000011141990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
102043003722500000006119900251010010910000100100005001067451130018300373003728588328745101002001000020010000300373022711102011009910010010000100000000000710116112991912100001003003830038300383003830038
10204300372240000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
10204300372250000000611990025101001001000010010000500106745103001830037300372858832874510157200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
10204300372250000000611990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
10204300372240000000611990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
10204300372240000000611990025101001001000010010000500106745113001830037300372858832874510100200100002001011330037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
10204300372250000000611990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038
10204300782250000000611990025101001001000010010000500106745103001830037300372858832874510100200100002001000030037300371110201100991001001000010000000000071011611299190100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830081
10024300372240611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
10024300372250611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frsqrte s0, s8
  frsqrte s1, s8
  frsqrte s2, s8
  frsqrte s3, s8
  frsqrte s4, s8
  frsqrte s5, s8
  frsqrte s6, s8
  frsqrte 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)03080b181e1f3f51inst 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)9fa6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204800426000000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010030000011151172160080036800001008004080040800408004080087
80204800395990000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800395990000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
802048003960000000704258010010080000100800005006400000800200800398003969971066999380100200800482008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800396000000039258010010080000100800005006400000800690800888003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800395990000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800395990000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800395990000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800395990000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040
80204800396000000039258010010080000100800005006400000800200800398003969971066999380100200800082008000880039800391180201100991001008000010000000011151170160080036800001008004080040800408004080040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024800396000050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203163380034080000108004080040800408004080040
80024800396000050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203172380034080000108004080040800408004080040
800248003960000502580010108000010800005064000008002080039800396998637001980010208000020800008003980039118002110910108000010000502031633800343180000108004080040800408004080040
80024800395990050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203163280034080000108004080040800408004080040
80024800396000071258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050202162380034080000108004080040800408004080040
80024800395990050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203164380034080000108004080040800408004080040
80024800396000050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203163380034080000108004080040800408004080040
80024800396000050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203163380034080000108004080040800408004080040
80024800395990050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203163380034080000108004080040800408004080040
80024800395990050258001010800001080000506400000800208003980039699863700198001020800002080000800398003911800211091010800001000050203163380034080000108004080040800408004080040