Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTN (scalar, S)

Test 1: uops

Code:

  frintn 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)030b1e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000373124112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723019861254725100010001000398160030183037303724143289510001000100030373037111001100000094116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230082254725100010001000398160030183037303724143289510001000100030373037111001100000073134112629100030383038303830383038
100430372401861254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400103254725100010001000399515030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724015103254725100010001000398160030183037303724143289510001000100030373037111001100002073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintn 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)030a0b18191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000073511611296330100001003003830038300383003830038
10204300372320000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003723200000048329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003723300000022529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372320000008229547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000100071011611296333100001003003830038300383003830038

1000 unrolls and 10 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)9fa6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403162229629010000103003830038300383003830038
100243003723200000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000206402162229629010000103003830038300383003830038
1002430037225000001052954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229667010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722400000822954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintn s0, s8
  frintn s1, s8
  frintn s2, s8
  frintn s3, s8
  frintn s4, s8
  frintn s5, s8
  frintn s6, s8
  frintn 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)03191e3f51inst 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)9fa8acc3c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184163320036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184164320036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163320036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183164320036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010010011151183163420036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163320036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182162420036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184162320036800001002004020040200402004020040
80204200391564303025801081008000810080020500640132020020200392003999776999080120200800322028003220039200391180201100991001008000010000011151183163320036800001002004020040200402004020040
80204200391550243025801081008000810080020500640132020023200392003999776999080120200800322008003220039200391180201100991001008000010000011151183162420036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b191e1f3f51inst 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)5f60696b6d6edispatch 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)9fa8acbranch mispredict (cb)cdcfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000004025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000050201816016162003680000102004020040200402004020040
800242003916100000014325800101080000108000050640000012002002003920039999631001980010208000020800002003920039118002110910108000010000050201616016162003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000012002002003920039999631001980010208000020800002003920039118002110910108000010000050201616016162003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000012002002003920039999631001980010208000020800002003920039118002110910108000010000050201716016162003680000102004020040200402004020040
8002420039156000000402580010108000010800005064000001200200200392003999963100198001020800002080000200392003911800211091010800001000005020161606162003680000102004020040200402004020040
800242003915500000040258001010800001080000506400000120020020039200399996310019800102080000208000020039200391180021109101080000100000502061601662003680000102004020040200402004020040
8002420039156000000402580010108000010800005064000001200200200392003999963100198001020800002080000200392003911800211091010800001000005020161606162003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000012002002003920039999631001980010208000020800002003920039118002110910108000010000050201716013132003680000102004020040200402004020040
8002420039155000000402580010108000010800005064000001200200200392003999963100198001020800002080000200392003911800211091010800001000005020161605162003680000102004020040200402004020040
800242003915500001770682580010108000010800005064000000200200200392003999963100198001020800002080000200392003911800211091010800001000005020161601552003680000102004020040200402004020040