Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTI (vector, 8H)

Test 1: uops

Code:

  frinti v0.8h, v0.8h
  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)030a1e3f4e51inst 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
1004303724206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037232126125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723206125472510001000100039816003018303730372414328951000100010003037308311100110000073216222629100030383038303830383038
10043037242012925472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037242126125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti v0.8h, v0.8h
  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)03080b1e1f3a3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000008229547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000003710116112963300100001003003830038300383003830038
1020430037232000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000003710116112963300100001003003830038300383003830038
1020430037232000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000710116112963322100001003003830038300383003830038
10204300372320000010329547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000710116112963300100001003003830038300383003830038
1020430037233000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000710116112963300100001003003830038300383003830038
1020430037241000006129547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000003710116112963300100001003003830038300383003830038
10204300372330000010329547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000710116112963300100001003003830038300383003830038
1020430037233000006129547251010010010000100100005004277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000000710116112963300100001003003830038300383003830038
1020430037233000006129547251010010010000100100005004277160130018300373003728264032874510100200100002001000030037300371110201100991001001000010000000710116112963300100001003003830038300383003830038
1020430037233000008729547251010010010000100100005004277160130018300373003728264732874510100200100002001000030037300371110201100991001001000010000020710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e1f3f4e51inst 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)9fa0a8a9acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330510139129547251001010100001010000504277160030018300373003728291328767100102010000201000030037300371110021109101010000104000006402162229629010000103003830038300383003830038
1002430037233048006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100300006402162229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003723301206129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003723300011729547251001010100001010000504277160030018300373007028286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10025300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000106402162229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372320006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti v0.8h, v8.8h
  frinti v1.8h, v8.8h
  frinti v2.8h, v8.8h
  frinti v3.8h, v8.8h
  frinti v4.8h, v8.8h
  frinti v5.8h, v8.8h
  frinti v6.8h, v8.8h
  frinti v7.8h, v8.8h
  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)031e3f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815603025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000611151182161120036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000311151182162120036800001002004020040200402004020040
802042003915603025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000611151181161220036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000057811151181161220036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000311151182162220036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000311151181162220036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000611151181161220036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182162120036800001002025620040200402004020040
8020420039155058258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100272311151182162220036800001002004020040200402004020040
802042003916103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182162120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a181e3a3f51inst 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)9fa0a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050156000004025800101080000108011250640000020020200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102009020040200402004020040
8002420039156000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050200116212003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000350200116112003680000102004020040200402004020040
8002420039164000904025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001003050200116112003680000102004020040200402004020040
8002420039155100004025800101080000108000050640000020020200392003999963100198001020800002080000200762003911800211091010800001000050200116112003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050200116112003680000102004020040200402004020040