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, S)

Test 1: uops

Code:

  frintm s0, s0
  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)03081e1f3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300010325472510001000100039816003018303730372414328951000100010003037303711100110000116273116112629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303725000612547251000100010003981600301830373037241432895100010001000303730371110011000058073116112629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372400061254725100010081000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000024873116122629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372400069254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303724000612547251000100010003981600301830373037241432895100010001000303730371110011000015173116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintm s0, s0
  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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000000214295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000100071021622296330100001003003830038300383003830038
10204300372330000000812295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000003071021622296330100001003003830038300383003830038
102043003723300000004282954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000002801273422966624100001003026630278302293027730038
10204300372330000000465295472510100100100001001000050042771600300183003730037282643287451010020210000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296990100001003003830038300383003830038
1020430037233000000082295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300183003730084282643287451027620810000200100003003730037111020110099100100100001000000200271021622296330100001003003830038300383003830038
10204300372330000000103295472510100100100001001000054242771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
10204300372320000000179295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730085111020110099100100100001000000000071021622296330100001003003830038300383003830038
10204300372330000000726295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18193a3f4e51inst 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)9fa0a1a6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400000214295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722500000382295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722500000612952944100191110016111015071427851230054301313008328295112880410237221032320104983013330133311002110910101000010402028430640216322962910000103013430132301323008530038
10024300372251112161295472510010101001610100005042771603009030132301302829082880510312201016120101623008430085311002110910101000010300028000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000130640216222962910000103003830038300383003830038
100243003722500000342295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722400000363295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722500000820295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
10024300372240000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722500000504295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintm s0, s8
  frintm s1, s8
  frintm s2, s8
  frintm s3, s8
  frintm s4, s8
  frintm s5, s8
  frintm s6, s8
  frintm s7, s8
  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)030f1e3f51inst 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)9facc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391550019225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118116020036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039155009525801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e1f3f51inst 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)9fa8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500016625800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020716632003680000102004020040200942004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316362003680000102004020040200402004020040
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616352003680000102004020040200402004020040
80024200391550608225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000305020316352003680000102004020040200402004020040
80024200391550008225800101080000108000050640000120020200392003999963100198001020802102080000200392003911800211091010800001000005020516642003680000102004020040200402004020040
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616532003680000102004020040200402004020040
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001010005020516532003680000102004020040200402004020040
80024200391560008225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516632003680000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316362003680000102004020040200402004020040
8002420039155000163825800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516352003680000102004020040200402004020040