Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPS (vector, 4H)

Test 1: uops

Code:

  fcvtps v0.4h, v0.4h
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037243383254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230156254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtps v0.4h, v0.4h
  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)030b181e3f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723300126129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130066300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296690100001003003830038300383003830038
102043003723200079029547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372320008929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723300126129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100073071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a1e3f4e51inst 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)9fa7a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640416342962910000103003830038300383003830038
10024300372250126129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316442962910000103003830038300383003830038
1002430037225106129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640416432962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640416342962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316342962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640416442962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767101592010000201000030037300371110021109101010000100000640416432962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640416442962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201017230037300371110021109101010000100000640316432962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000668316342962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtps v0.4h, v8.4h
  fcvtps v1.4h, v8.4h
  fcvtps v2.4h, v8.4h
  fcvtps v3.4h, v8.4h
  fcvtps v4.4h, v8.4h
  fcvtps v5.4h, v8.4h
  fcvtps v6.4h, v8.4h
  fcvtps v7.4h, v8.4h
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391560302580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100918111511801600120036800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010040111511801600020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100110111511801600020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010073111511801600020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010066111511801600020036800001002004020040200402004020040
80204200391550220258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010060111511801600020036800001002004020040200402004020040
80204200391550605258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010086111511801600020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000132111511801600020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010033111511801600020036800001002004020040200402004020040
8020420039155030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010000111511801600020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3a3f51inst 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)9fa0a1a7a8a9acc2cfd5d6d9ddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155000000004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
8002420039155000000006825800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
8002420039156000000004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000010005020116011200360080000102004020040200402004020040
8002420039156000110004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000005020116011200360080000102004020040200402004020040
800242003915500000000402580010108000010800005064000002002020039200399989310012800102080000208000020039200391180021109101080000100000017105020116011200360080000102004020040200402004020040
8002420039155000000008625800101080000108000050640000020020200392003999893100128001020800002080000200392003911800211091010800001000000905020116011200360080000102004020040200402004020040