Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64Z (scalar, D)

Test 1: uops

Code:

  frint64z d0, d0
  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)031e3a3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037231206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073133112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240032225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64z d0, d0
  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)030e191e1f3a3f4e51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320000014529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330000014529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100021207101161129633100001003003830038300383003830038
10204300372320000024529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001007101161129633100001003003830038300383003830038
10204300372330000012429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330000018729547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000037101161129633100001003003830038300383003830038
10204300372330000023129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330000014729547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372320000055029547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330000043729547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330000036929547251010010010000100100005004277160130018300373007028264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3f4e51inst 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
1002430037225000002036061295472510010101000812101505042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229686010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010161301333008411100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000200006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64z d0, d8
  frint64z d1, d8
  frint64z d2, d8
  frint64z d3, d8
  frint64z d4, d8
  frint64z d5, d8
  frint64z d6, d8
  frint64z d7, d8
  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)0308191e1f3f51inst 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)9fa8a9abacc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058156000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181160020036800001002004020040200402004020040
8020420039155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000311151180160020036800001002004020091200402004020040
8020420039156000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392009031802011009910010080000100000011151380160020036800001002004020040200402004020040
80204200391560000156258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039156000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550012030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)6061696d6edispatch 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)9fa8cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915055425800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100502000416332003680000102004020040200402004020040
80024200391504025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000316432003680000102004020040200402032620040
80024200391508225800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000316332003680000102004020040200402004020040
80024200391504025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000316332003680000102004020040200402004020040
80024200391494025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000316332003680000102004020040200402004020040
800242003915023325800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000316332003680000102004020040200402004020040
80024200391504025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000316322003680000102004020040200402004020040
80024200391506325800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100502000316232003680000102004020040200402004020040
80024200391508225800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000101502000316332009780000102004020040200402004020040
80024200391504025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100502000216322003680000102004020040200402004020040