Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT32X (scalar, S)

Test 1: uops

Code:

  frint32x 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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)6061696d6edispatch 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)a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723010325472510001000100039816010301830373037241432895100010001161303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816010301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32x 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)0308090b18191e1f3f4e51inst 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)72scheduler 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320000000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
102043003723300000005362954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372330000030612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
102043003723300000002322954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038
10204300372410000000612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000000000710216222963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)79~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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300061295472510010101000010100005042771601300183003730037282863287671001002010000201000030037300371110021109101010000100000640616222962910000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100002705640216222962910000103003830038300383003830038
10024300372410002292954725100101010000101000050427716003001830037300372828632876710010102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830085
100243003723300061295472510010101000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100100640216222962910000103003830038300383003830038
1002430037232000103295472510010101000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003723313960103295382510010131000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100100640216222962910000103003830038300383003830038
100243003723200061295472510010101000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037233000103295472510010101000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100140640216222962910000103003830038300383003830038
1002430037233090103295472510010101000010100005042771600300183003730084282863287671001002010000201000030037300371110021109101010000100100640216222962910000103003830038300383003830038
100243003723200061295472510010101000010100005042771600300183003730037282863287671001002010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32x s0, s8
  frint32x s1, s8
  frint32x s2, s8
  frint32x s3, s8
  frint32x s4, s8
  frint32x s5, s8
  frint32x s6, s8
  frint32x s7, s8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155000012004025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000303011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039156000039003025801081008030110080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000003011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003916100000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000100011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000100011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100002800011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e3f51inst 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)9fa7a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156000006125800101080000108000050640000120020200392003999963100198001020800002080000200392003921800211091010800001001005020624882003680000102004020040200402004020040
80024201561621111040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010036005020616682003680000102004020040200402004020040
80024200391560000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010052005020616872003680000102004020040200402004020040
8002420039155000004025800101080000108010550640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516562003680000102004020040200402004020040
80024200391560000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010030315020716772003680000102004020040200402004020040
80024200391560000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010024305020516652003680000102004020040200402004020040
80024200391550000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010036005020516672003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020716652003680000102004020040200402004020040
8002420039155000006825800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616752003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001007005020516552003680000102004020040200402004020040