Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNMV (4S)

Test 1: uops

Code:

  fmaxnmv s0, v0.4s
  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
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723025125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000973116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723014725472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013021303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fmaxnmv s0, v0.4s
  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)0307080b1e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000361295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000082295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383008530274
1020430037225000120061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
1020430037225000000536295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000084295472510100100100001001000050042771601300183003730037282649287451056820010000200100003003730037111020110099100100100001004400002071011611296330100001003003830038300383003830038
102043008622500001761170295472510100100100001001000050042771600300183003730037282643287451010020010000204100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000171011611296330100001003003830038300383003830038

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400000000612954725100101010000101000050427716003001830037300372828632876710164201000020100003003730037111002110910101000010000000064021611229629010000103003830038300383003830038
10024300372240000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372240000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601301263003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000005100398295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402492229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372240000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372360000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000306402162229629010000103003830038300383003830038
10024300372250000000061295476210010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722400000000170295472510010101000010100005042771601300183003730037282863287671001020100002010000300373009811100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fmaxnmv s0, v8.4s
  fmaxnmv s1, v8.4s
  fmaxnmv s2, v8.4s
  fmaxnmv s3, v8.4s
  fmaxnmv s4, v8.4s
  fmaxnmv s5, v8.4s
  fmaxnmv s6, v8.4s
  fmaxnmv s7, v8.4s
  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)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)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)9fa8acc5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010030111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
802042003915001562580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010003111511816020036800001002004020040200402004020040
802042003915001162580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511816020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b191e3f51inst 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)9fa0a8acc2branch mispredict (cb)cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200151614132003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100002050240141611112003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050240171612122003680000102004020040200402004020040
800242003915000001262580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200131616132003680000102004020040200402004020040
800242003915000001282580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200141616122003680000102004020040200402004020040
800242003915000001472580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200181615122003680000102004020040200402004020040
8002420039150000061258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005024014161492003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200161617152003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100500050260161612162003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200121613162003680000102004020040200402004020040