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, D to D)

Test 1: uops

Code:

  fcvtas 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
10043037231210325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003020303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951057100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037231210325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas 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)030b181e1f3f4e5051inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000612954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021611296330100001003003830038300383003830038
10204300372330000612954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830071300383003830038
10204300372330000612954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000003071011611296330100001003003830038300383003830038
102043003723200007262954702510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611297050100001003003830038300383003830038
102043003723300008452954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330000612954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372330000612954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000010071011611296330100001003003830038300383003830038
10204300372330000612954702510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003723300120612954702510100100100001001000050042776340300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830069
10204300372410000612954702510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b1e1f3f4e51inst 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)9fa6a8a9acc2cfitlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003724100000115295472510010101000010100005042771600300183300373003728286252876710010201017820100003003730037111002110910101000010000006400316432962910000103003830038300383003830038
10024300372410000053929547251001010100001010000504277160130018030037300372828632878810010201000020100003003730037111002110910101000010020006400416442962910000103003830038300383003830038
100243003723300024046729547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000006400416342964010000103003830038300383003830038
1002430037241000006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000006400416432962910000103003830038300383008530038
10024300372460000023229547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010010006400416432962910000103013130132301333013330132
1002430131242101132240199529529611003912100081110158714284777030018030037300372828632876710010201000020100003003730037111002110910101000010000006400416432962910000103003830038300383003830038
10024300372410000025329547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000006400316342962910000103003830038300383003830038
100243003724100015018029547251001010100001010000504277160130018030037300372828632876710158201000020100003003730037111002110910101000010020006400416342962910000103003830038300383003830083
1002430037241000006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000006400416342962910000103003830038300383003830038
10024300372410000072629547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000306400416342962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas d0, d8
  fcvtas d1, d8
  fcvtas d2, d8
  fcvtas d3, d8
  fcvtas d4, d8
  fcvtas d5, d8
  fcvtas d6, d8
  fcvtas 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)03041e1f3a3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815500003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001002011151181160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001002311151180160020036800001002004020040200402004020040
8020420039156000021425801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001004011151180160020036800001002004020040200402004020040
802042003915600003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001011151180160020036800001002004020040200402004020040
802042003915600003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000611151180160020036800001002004020040200402004020040
80204200391560000695258010810080008100800205006401320200200200392003999776999080120200800322008003220039200392180201100991001008000010040011151180160020036800001002004020040200402004020040
802042003915500009525801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001002011151180160020036800001002004020040200402004020040
80204200391560000302580108100800081008002050064013202002002003920039997769990801202008003220080032200392003911802011009910010080000100447811151180160020036800001002004020040200402004020040
8020420039155000074925801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001005011151180160020036800001002004020040200402004020040
802042003915500003025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001009311151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040708090b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6daddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155200000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039156000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000010000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040
8002420039155000000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502011601120036080000102004020040200402004020040