Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXV (8H)

Test 1: uops

Code:

  fmaxv h0, v0.8h
  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)033f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037226125472510001000100039816030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
100430372325125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037236125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037236125472510001000100039816030183037303724143289510001000100030373037111001100024073116112629100030383038303830383038
10043037236125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037226125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037236125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037236125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372215325472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372315625472510001000100039816030183037303724143289510001000100030373037111001100020373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fmaxv h0, v0.8h
  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)03080b191e1f3a3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129520251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100003712307101161129633100001003003830038300383003830038
102043003722501000061295472510142100100001001000050042771600300183003730037282643287451010020010000200106643003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003722600000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
1020430037225000000124295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037211020110099100100100001002223557507551161129633100001003003830038300383003830038
10204300372250003301760612954725101001001000010010000546427851203001830131301342826832874510100200100002001000030037300371110201100991001001000010000215707101161129633100001003003830038300383003830038
102043013222511000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000002007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003007101161129633100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000307101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000000277295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000001448295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000210166295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006405162229629010000103003830038300383003830038
1002430037225000000522295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000000526295472510010101000010101505042771603001830037300372828632876710010201000020100003003730037111002110910101000010004006402162229629010000103003830038300383003830038
10024300372250000564061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fmaxv h0, v8.8h
  fmaxv h1, v8.8h
  fmaxv h2, v8.8h
  fmaxv h3, v8.8h
  fmaxv h4, v8.8h
  fmaxv h5, v8.8h
  fmaxv h6, v8.8h
  fmaxv h7, v8.8h
  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)03070a18191e1f3f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182161120036800001002004020040200402004020040
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915011000089925801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220099200391180201100991001008000010001311151181161120036800001002004020040200402004020040
802042003915011000089825801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501100005125801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010006311151181171120036800001002004020040200402004020040
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
80204200391501100003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040

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)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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115007882580090108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
800242003915608222580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500100025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010021005020116112003680000102004020040200402004020040
800242003915003202580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000050201161232003680000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150010992580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
800242003915009842580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150010742580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040