Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT32X (scalar, D)

Test 1: uops

Code:

  frint32x 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)0308090b18191e3a3f4e51inst 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)a0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000000061254725100010001000398160030183037303724143289510001000100030373037111001100000000073316222629100030383038303830383038
10043037230000000307254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
10043037230000000123254725100010001000398160030183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
10043037240000000147254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
10043037240000000483254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
10043037230000000414254725100010001000398160030183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
10043037230000000105254725100010001000398160030183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
1004303724000000061254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038
1004303724000000061254725100010001000398160130183037303724143289510001000100030373037111001100000003073216222629100030383038303830383038
1004303723000000061254725100010001000398160130183037303724143289510001000100030373037111001100000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32x 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)0318191e3f4e51inst 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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200012429547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030054030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037233000263029547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010001007101161129633100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372410006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723300020829547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372330006129547251010910010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723300010329547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037241027182954725100101010000101000050427716003001830037301802829132876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722502082954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722504832954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250842954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722505072954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722501052954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372240612954725100101010000101000050427716003001830037300372828632876710010201001220100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722502502954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722501052954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32x d0, d8
  frint32x d1, d8
  frint32x d2, d8
  frint32x d3, d8
  frint32x d4, d8
  frint32x d5, d8
  frint32x d6, d8
  frint32x d7, d8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030a18191e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010010011151181600020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
8020420039155000018502580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010010011151181600020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
80204200391560000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
802042003915500006952580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181600020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010013011151181600020036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03080b0f1e3f51inst 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)9fa0a1a8accfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511550001282258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000950200201671020036080000102004020040200402004020040
80024200391550000822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502007168520036080000102004020040200402004020040
800242003915600004025800101080000108000050640000020020200392018999963100198001020800002080000200392003911800211091010800001000365020016169420036080000102004020040200402004020040
80024200391610000402580010108000010800005064000012002020039200399996310019804322080000208000020039200391180021109101080000100000502005169920036080000102004020040200402004020040
8002420039155000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050200816121020036080000102004020040200402004020040
800242003915500006825800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000035020013168620036080000102004020040200402004020040
80024200391560000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502009166920036080000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502007165920036080000102004020040200402004020040
800242003915500001052580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502006165920036080000102004020040200402004020040
80024200391550004624025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000105020071610920036080000102004020040200402004020040