Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTN (vector, 4S)

Test 1: uops

Code:

  frintn v0.4s, v0.4s
  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)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
1004303724276125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372336125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723426125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintn v0.4s, v0.4s
  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)03080b18191e1f3f4e51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000105071011611296330100001003003830038300383003830038
10204300372331000120612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000096071011611296330100001003003830038300383003830038
102043003723200000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000006071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000005565071011611296330100001003003830038300383003830038
10204300372320000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000183071011611296330100001003003830038300383003830038
1020430037232000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000078071011611296330100001003003830038300383003830038
102043003723300000010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000186071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000000842954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000011083071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037232000012006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003724100000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003723300000006129547251001010100001010000504279864030018300373003728286328767100102010329201000030037301311110021109101010000100000005615006822162229701010000103003830038300383003830038
1002430037233010000018529547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830086
1002430037233000000060729547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003723300000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003723300000006129547251001010100001010000504277160030018300373003728286328767101632010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000000072629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000000044129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383008430038
100243003722500000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000016402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintn v0.4s, v8.4s
  frintn v1.4s, v8.4s
  frintn v2.4s, v8.4s
  frintn v3.4s, v8.4s
  frintn v4.4s, v8.4s
  frintn v5.4s, v8.4s
  frintn v6.4s, v8.4s
  frintn v7.4s, v8.4s
  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)030918191e3f51inst 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)61696d6edispatch 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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391550000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000311151180160020036800001002004020040200402004020040
802042003915500030302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550000722580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100001011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100006011151180160020036800001002004020040200402004020040
80204200391550100582580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100001611151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100000911151180160020036800001002004020040200402004020040
80204200391550000582580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100001011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a1e3f51inst 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)9fa1a6a8a9accfd0d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000900502002162220036080000102004020040200402004020040
80024200391550007052580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010001306502002162220036080000102004020040200402004020040
8002420039155000822580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010001500502002162220036080000102004020040200402004020040
800242003915500040258001010801951080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000200502002162220036080000102010820040200402039720040
800242003915500040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000000502002162220036080000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999603100198001020800002080000200392003911800211091010800001000500502002162220036080000102004020040200402004020040
8002420039155000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010002703502002162220036080000102004020040200402004020040
8002420039155000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010002600502005162220036080000102004020040200402004020040
8002420039155000402580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010003003502002162220036080000102004020040200402004020040
8002420039155000822580010108000010800005064000002002020039200399996031001980010208000020800002003920039118002110910108000010002803502002162220036080000102004020040200402004020040