Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNMV (4H)

Test 1: uops

Code:

  fmaxnmv h0, v0.4h
  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
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
1004303723017725472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723246125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fmaxnmv h0, v0.4h
  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)030b18191e1f3f4e51inst 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000141061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003722500018061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372240003061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372250000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003722400018061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000028080007101161129633100001003003830038300383003830038
1020430037225000270061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003722500027061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372250000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000300007101161129633100001003003830038300383003830038
102043008423600027061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
1020430037225000435061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000106402162229629010000103003830038300383003830038
10024300372250961295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001020336402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000106402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250082295472510010101000010100005042771600300183003730037282863287671016220100002010000300373003711100211091010100001000036402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fmaxnmv h0, v8.4h
  fmaxnmv h1, v8.4h
  fmaxnmv h2, v8.4h
  fmaxnmv h3, v8.4h
  fmaxnmv h4, v8.4h
  fmaxnmv h5, v8.4h
  fmaxnmv h6, v8.4h
  fmaxnmv h7, v8.4h
  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)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)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)9fa0a1a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150012302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100000008711151180160020036800001002004020040200402004020040
802042003915011230258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020254200402004020040
802042003915001276258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000010011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002002003920039997769990801202008003220080032200392003911802011009910010080000100000220611151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000010011151180160020036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391502740258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010006005020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010001805020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010005705020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200200200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040