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, H)

Test 1: uops

Code:

  frecpx h0, h0
  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)03091e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372200611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372200611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372300611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303723012611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frecpx h0, h0
  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)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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
10204300372250611990025101001001000010010000500106745103001830037300372858803287451010020010000200100003003730037111020110099100100100001001871011611299190100001003003830038300383003830038
1020430037225061199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
1020430037225061199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830260300383003830038
1020430037225061199002510100100100001001000050010676120300183003730037285883328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
1020430037225066199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
102043003722516261199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100371011611299190100001003003830038300383003830038
1020430037225061199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038
1020430037225061199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003008430086300383003830038
1020430037225061199002510100100100001001000050010674510300183003730037285880328745101002001000020010000300373003711102011009910010010000100071011611299190100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000006402162229919010000103003830038300383003830038
1002430037225000000006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000006402162229919010000103003830038300383003830038
1002430037225000000006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000006402162229919010000103003830038300383003830038
1002430037225000000006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000006402162230134210000103031830323303233022730323
100243032122710167945616020841980415010018111005615102526610685780302343036930321287352928945102632010343201040230074303676110021109101010000102010710807392734530173310000103032330274303683040530322
100243035822711066927616126781980413810029131005610102945010684170302703031930319287343428956103172010343221039630419301318110021109101010000100012817007403723230170410000103036930370304153037330320
10024303702280117893670406119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000006402162229919010000103003830038300383003830038
1002430037225000000006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000016402162229919010000103003830038300383003830038
1002430037225000000006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000006402162229919010000103003830038300383003830038
1002430037225000000006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000006402162229919010000103008630038300383003830038

Test 3: throughput

Count: 8

Code:

  frecpx h0, h8
  frecpx h1, h8
  frecpx h2, h8
  frecpx h3, h8
  frecpx h4, h8
  frecpx h5, h8
  frecpx h6, h8
  frecpx h7, h8
  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)03181e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802048003959900392580100100800001008000050064000008002080039800396997166999380100200800082008000880039800391180201100991001008000010013911151170160080036800001008004080040800408004080040
802048003959900704258010010080000100800005006400001800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
802048003960000704258010010080000100800005006400001800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
802048003960000229258010010080000100800005006400001800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
80204800395990039258010010080000100800005006400001800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
80204800396000039438010010080000100800005006400001800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
80204800395990039258010010080000100800005006400000800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
80204800396000039258010010080000100800005006400000800208003980039699716699938013520080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
80204800396000039258010010080000100800005006400000800208003980039699966699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040
80204800395990039258010010080000100800005006400000800208003980039699716699938010020080008200800088003980039118020110099100100800001000011151170160080036800001008004080040800408004080040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a18191e1f3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024800395990100000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020191620138003480000108004080040800408004080040
80024800395990000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020121622178018780000108004080040800408004080040
80024800396000000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020141626128003480000108004080040800408004080040
80024800396000000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020131624128003480000108004080040800408004080040
80024800396000000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020131621158003480000108004080040800408004080040
80024800396000000000502580010108000010800005064000018002080039800396998637001980010208000020800008008880039118002110910108000010000005020121617168003480000108004080040800408004080040
80024800396000000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020131627188011180000108004080040800408004080040
80024800396000000000712580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020121620168003480000108004080040800408004080040
80024800396000000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000005020121619178003480000108004080040800408004080040
80024800395990000000502580010108000010800005064000018002080039800396998637001980010208000020800008003980039118002110910108000010000015020101625148003480000108004080040800408004080040