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, 2D)

Test 1: uops

Code:

  fcvtas v0.2d, v0.2d
  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)696d6edispatch 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
100430372401282547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110001073216112629100030383038303830383038
100430372404022547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383086303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000075116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000375216122629100030383038303830383038
100430372404132547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724121872547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas v0.2d, v0.2d
  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)03080b191e1f3f4e51inst 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)9fa0a1a8acc2c5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300853003830038
102043003723310000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002101000030037300371110201100991001001000010040230007101161129633100001003007530038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003724100000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000190007101161129633100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e1f3f4e51inst 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)72scheduler 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)9fa6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006404482229629010000103003830038300383003830038
1002430037225010006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002530037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010030006402162229629010000103003830038300383003830038
1002430037239000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629210000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006403162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas v0.2d, v8.2d
  fcvtas v1.2d, v8.2d
  fcvtas v2.2d, v8.2d
  fcvtas v3.2d, v8.2d
  fcvtas v4.2d, v8.2d
  fcvtas v5.2d, v8.2d
  fcvtas v6.2d, v8.2d
  fcvtas v7.2d, v8.2d
  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)030818191e1f3a3f51inst 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
8020420058155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915500012001252580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039156000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020081800001002004020040200402004020040
8020420039156000300302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050156000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502093116212120036080000102004020040200402004020040
8002420039155000001152580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200211621920036080000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000507402116212120036080000102004020090200402004020040
800242003915601000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101050200211692120036080000102004020040200402004020040
800242003915600000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200141692120036080000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502002116212120036080000102004020040200402004020040
8002420039161000008225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001010502002116212120036080000102004020040200402004020040
800242003915500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100350200211692120036080000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200211692120036080000102004020040200402004020040
800242003915600000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200211692120036080000102004020040200402004020040