Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (scalar, integer, S to S)

Test 1: uops

Code:

  fcvtzs 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)030b181e3f4e51inst 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230013261254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383085
100430372300061254725100010001000398160030183037303724143291410001000100030373037111001100000073216222629100030383038303830383038
1004303723000612547251000100010003981601301830373037241432914100010001000303730371110011000330073216222629100030383038303830383038
100430372310061254725100010001000398160030183084303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100003073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723001261254725100010001000398160030183037303724143289510001000100030373037111001100003073216222629100030383038303830383038
1004303724000251254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs 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)030818191e1f3a3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000126295472510100100100001001000050042771600300183008830037282648287451010020410000200100003008530084211020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500090061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071013311296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003008430037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000204100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000010371011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001141000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000491295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000002640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000000640216222962910000103003830038300383003830038
1002430037225000347295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000001230640216222962910000103003830038300383003830038
1002430037225000232295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000000640216222962910000103003830038300853008530038
1002430037232000789295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000000640216222962910000103003830038300383003830038
1002430037225000103295472510010101000010100005042771600300183003730037282863287671016220100002010000301333003711100211091010100001002010000661216422962910000103003830038300383003830038
1002430037225000885295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000028580640216222962910000103003830038300383003830038
1002430037225000508295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000000640216222962910000103003830038300383003830038
10024300372250120877295472510010101000010100005042771600300183003730037282863287671001020100002010172300373003711100211091010100001000000000640216422973710000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs s0, s8
  fcvtzs s1, s8
  fcvtzs s2, s8
  fcvtzs s3, s8
  fcvtzs s4, s8
  fcvtzs s5, s8
  fcvtzs s6, s8
  fcvtzs 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)0308090b18191e1f3f51inst 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
8020420058155000006990302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550000033306952580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391560000000302580108100800081008002050064013202002020039200399977699908012020080032200801362011620039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391610000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550000000302580108100800081008002051864013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391560000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001001011151180161020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200422009099776100168012020080032200800322003920039118020110099100100800001000311151180160020036800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

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)9fa0a1a6a8accdcfd0d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050161040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000000502001816016162003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020201732009210013310019800102080000208000020039200391180021109101080000100000005020061606162003680000102004020040200402004020040
8002420039155124025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000010050200161601362003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502001516216172003680000102004020040200402004020040
800242003916134025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200161606162003680000102004020040200402004020040
8002420039155068258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502001616016112003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200161601662003680000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502001616016162003680000102004020040200402004020040
80024200391550402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000305020061606162003680000102004020040200402004020040
80024200391550822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020061606132003680000102004020040200402004020040