Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTM (scalar, H)

Test 1: uops

Code:

  frintm 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)0318191e1f3f4e51inst 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)a0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300306125472510001000100039816013018303730372414328951000100010003037303711100110000030094216112629100030383038303830383038
1004303724000021525472510001000100039816003018303730372414328951000100010003037303711100110000003073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372200006125472510001000100039816013018303730372414328951000114611623085307321100110002001073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383086303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372200006125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
1004303722001506125472510001000100039816003018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951050100011683037308511100110000000073116112629100030383038303830383038
100430372200006125472510001000100039816013018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintm 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)0318191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000103295472510100100100001001000050042771600300183003730037282716287411010020010008200100083003730037111020110099100100100001000011171801600296460100001003003830038300383003830038
1020430037225003061295472510100100100001001000050042771600300183003730037282717287411010020010008200100083003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282716287411010020010008200100083003730037111020110099100100100001000011171701600296450100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282716287401010020010008200100083003730037111020110099100100100001000011171701600296460100001003003830038300383003830038
10204300372240090383295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000710116112963326100001003003830038300383003830038
10204300372240000103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430131260110152808229547251001012100081110150504278512030054301303008428291102878610010201016120100003003730037111002110910101000010243110040640716232966710000103003830085300383003830086
10024300852600032360108139029520251001010100001010150554277160030018300373003728291202878710163201048620101623017730133111002110910101000010202000320640216232962910000103003830038300383003830038
1002430037241000060612954731100101010000101030050427716003001830037300852829272876710010201000020100003003730084111002110910101000010000000000640216222962910000103003830038300383003830038
1002430037241000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000000640216222962910000103003830038300383003830038
1002430037241000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000000640216222962910000103003830038300383003830038
10024300372410000007262954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000000640216222962910000103003830038300383003830038
10024300372320000120612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000000640216222962910000103003830038300383003830038
100243003723300005700612954725100101010000101000050427716003001830037300372828632876710010201000020101613003730037111002110910101000010000000000640223222962910000103003830038300383003830038
1002430037229000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000000640216222962910000103003830038300383003830038
1002430037229000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintm h0, h8
  frintm h1, h8
  frintm h2, h8
  frintm h3, h8
  frintm h4, h8
  frintm h5, h8
  frintm h6, h8
  frintm h7, h8
  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)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)9fa0a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000101115118116020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010001901115118016020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010002001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000301115118016020036800001002004020040200402004020040
802042003915503025801081008000810280020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000101115118016020098800001002004020040200402004020040
802042003915512695258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000691115118016020036800001002004020040200402004020040
802042003916003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
8020420039155072258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000661115118016020036800001002004020040200402004020040
8020420039155123025805081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000101115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a18191e1f3a3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501550000000070525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020416552003680000102004020040200402004020040
80024200391550000012008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020516652003680000102004020040200402004020040
80024200391550000012004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020416652003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020616562003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020516762003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020616652003680000102004020040200402004020040
8002420039156000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020616572004680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020716552003680000102004020040200402004020040
8002420041156000000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001002000005020616662003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000005020516572003680000102004020040200402004020040