Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAU (scalar, D to D)

Test 1: uops

Code:

  fcvtau 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)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
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073316222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000373316332629100030383038303830383038
1004303724126125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110001073316332629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038
100430372308425472510001000100039816013018303730372414328951000100010003037303711100110000073316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau 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)0307080a0b18191e1f243f4e51inst 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)696d6edispatch 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
1020430037233000000120061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000171011611296330100001003003830038300383003830038
102043003723300000000089295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003723200000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300873003830038
1020430037232000000000726295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043008023300000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003723200000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
102043003723200000000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e3f4e51inst 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)696d6edispatch 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240961295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722503661295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372320061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250661295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722401561295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250361295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722501861295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629210000103003830038300383003830038
100253003722505161295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722501861295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau d0, d8
  fcvtau d1, d8
  fcvtau d2, d8
  fcvtau d3, d8
  fcvtau d4, d8
  fcvtau d5, d8
  fcvtau d6, d8
  fcvtau 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)0308191e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
8020420039155009302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010007211151180160020036800001002004020040200402004020040
8020420039155003302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915600058258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100013511151180160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039156000582580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039156000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001511151180160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402011520040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e3f51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500008225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020516342003680000102004020040200402004020040
800242003915500006825800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416442003680000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000105020416432003680000102004020040200402004020040
8002420039155100095225800101080000108000050640000120020200392003999966100198001020800002080000201562015411800211091010800001003005020316442003680000102004020040200402004020040
800242014015600004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020416342003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000105020416342003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000105020416442003680000102004020040200402004020040
800242003915500008225800101080000108000050640000020020200392003999963100198001020800002080000200892009211800211091010800001000005020416342003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000105020316442003680000102004020040200402004020040
800242003915500008325800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000035020416432003680000102004020040200402004020040