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, 2S)

Test 1: uops

Code:

  fcvtas v0.2s, v0.2s
  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
1004303723022425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724126125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723012525472510001000100039816003018303730372414328951000100010003037303711100110000073116112700100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723633625472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas v0.2s, v0.2s
  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)03080b18191e1f3a3f4e51inst 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)5f60696d6edispatch 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)9fa0a1a7a8a9acc5branch mispredict (cb)cdcfd0icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000000822953825101001001000010010000500427716000300183003730037282716287411010020010008200100083003730037111020110099100100100001000000001117180001600296450100001003003830038300383003830038
102043003723200001200612954725101001001000010010000500427716000300183003730037282717287401010020010008200100083003730037111020110099100100100001000000000007100011611296330100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000001007100011611296330100001003003830038300383003830038
102043003723200000001262954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000010000007100011611296330100001003003830038300383003830038
102043013223310000007262954725101001001000010010000500427716000300183003730037282643287451025720010000200100003003730037111020110099100100100001000000000007100011611296330100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000007391011611296330100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000007100011611296330100001003003830038300383003830038
10204300832330100144007932952063101001001000810010150500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000001000007100011611296330100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716000300183003730037282643287451056620010000200100003003730037111020110099100100100001000001030007100011611296330100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716000300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000007100011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307181e1f3f4e51inst 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)9fa1a8a9acbranch mispredict (cb)cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037241000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030071300371110021109101010000100000064002162229629010000103003830038300383003830038
1002430037233000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002162329629010000103003830038300383003830038
1002430037233000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
1002430037233003061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002162329629010000103003830038300383003830038
10024300372320000103295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000064002164229629010000103003830038300383003830038
1002430037232000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
1002430037233000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002163229629010000103003830038300383003830038
1002430037233000066295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
1002430037233000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002163229629010000103003830038300383003830038
1002430037232000061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629110000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas v0.2s, v8.2s
  fcvtas v1.2s, v8.2s
  fcvtas v2.2s, v8.2s
  fcvtas v3.2s, v8.2s
  fcvtas v4.2s, v8.2s
  fcvtas v5.2s, v8.2s
  fcvtas v6.2s, v8.2s
  fcvtas v7.2s, v8.2s
  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)0304080a0b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039156000000540030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811600200360800001002004020040200402004020040
802042003915500000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915600000000030258010810080008100800205006401321200792003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915600000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915600000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000003111511801600200360800001002004020040200402004020040
802042003915500000090030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801600200360800001002004020040200402004020040
802042003915500000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000200111511801600200360800001002004020040200402004020040
8020420039155000000120030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000003111511801700200360800001002004020040200402004020040
802042003916100000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111512001600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)5f6061696d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915503051525800101080000108000050640000010200202003920039999631001980010208000020800002003920039118002110910108000010005020003316552003680000102004020040200402004020040
8002420039156004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000216222003680000102004020040200402004020040
8002420039155004025800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010035020000416432003680000102004020040200402004020040
8002420039155004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000216422003680000102004020040200402004020040
80024200391610031225800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000316322003680000102004020040200402004020040
8002420039156004025800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010105020000216322003680000102004020040200402004020040
8002420039156008225800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020000216332003680000102004020040200402004020040
8002420039156004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020540216322003680000102004020040200402004020040
8002420039155004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010005020001216332003680000102004020040200402004020040
8002420039156008225800101080000108000050640000010200202003920039999631001980010208000020800002003920039118002110910108000010005020000316222003680000102004020040200402004020040