Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAS (scalar, S to S)

Test 1: uops

Code:

  fcvtas 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)03181e3f4e51inst 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
10043037230010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301210625472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724008425472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230010325472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037240010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas 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)030b18191e3f4e51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
1020430037232000456129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
102043003723300006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
1020430037233000336129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
1020430037233000666129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009901001001000010000200710216222963300100001003003830038300383003830038
1020430037232000246129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
10204300372320004206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000003710216222963300100001003003830038300383003830038
1020430037232000336129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
1020430037233000666129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000000710216222963300100001003003830038300383003830038
1020430037232000636129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009901001001000010000003710216222963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722537262954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629210000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250662954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010736402162229661010000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010221000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372240612954725100101010000101000061427716003001830037300372828632876710010201000020100003003730037111002110910101000010006682162229629010000103003830038300383003830038
10024300372320822954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402161229629010000103003830038300383003830038
100243003722505932954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722501492954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300842240612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402163229629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas s0, s8
  fcvtas s1, s8
  fcvtas s2, s8
  fcvtas s3, s8
  fcvtas s4, s8
  fcvtas s5, s8
  fcvtas s6, s8
  fcvtas 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)031e1f3f51inst 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)9fa0a7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061155300302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000003011151180160020036800001002004020040200402004020040
8020420039155603025801081008000810080020500640132020020200392003999779100158012020080032200800322003920039118020110099100100800001000013011151180160020036800001002004020040200402004020040
8020420039155330302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915530302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000010011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015504025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516432003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416442003680000102004020040200402004020050
8002420039155214025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020416442003680000102004020040200402004020040
80024200391551959625800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416442003680000102004020040200402004020040
8002420039161814025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316432003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316342003680000102004020040200402004020040
800242003916104025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316432003680000102004020040200402004020040
800242003915604025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416442003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020616442003680000102004020040200402004020040
8002420039155158225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000305020416342003680000102004020040200402004020040