Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAS (vector, 8H)

Test 1: uops

Code:

  fcvtas 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)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)a8c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372396125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372506125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372466125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303721100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas 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)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)60696b6d6edispatch 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)9fa1a8a9accdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102053003723201732954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000100071011611296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003723312612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372320612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003723306312954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000074111611296330100001003003830038300383003830038
10204300372330612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372320612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372320612954725101001021000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110901010100001000000640616222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
100243003722501342954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110901010100001000000640216462962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038
10024300372240612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110901010100001000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas v0.8h, v8.8h
  fcvtas v1.8h, v8.8h
  fcvtas v2.8h, v8.8h
  fcvtas v3.8h, v8.8h
  fcvtas v4.8h, v8.8h
  fcvtas v5.8h, v8.8h
  fcvtas v6.8h, v8.8h
  fcvtas 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)030b191e3a3f51inst 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)9fa0a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204202151551000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402009120040
80204200391560300932580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391560000932580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204201041550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550000522580108100800081008012550064013212008320039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500120742580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500002542580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550000762580108100800081008002050064013202002020039200399977699908012020080350200800322003920039218020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500005412580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500307225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000302111151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3a3f51inst 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)9fa0a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000014625800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050207163320036080000102004020040200402004020040
80024200391550012009925800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050204163320036080000102004020040200402004020040
80024200391550000010925800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000030050203163320036080000102004020040200402004020040
800242003915500900182025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050204163320036080000102004020040200402004020040
8002420039155000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050203163720036080000102004020040200402004020040
80024200391550000055125800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050203164720036080000102004020040200402004020040
80024200391610060064525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050203167420036080000102004020040200402004020040
8002420039155000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050203163320036080000102004020040200402004020040
8002420039155003600171225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050203163320036080000102004020040200402004020040
8002420039155000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000030050203163320036080000102004020040200402009120040