Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMS (scalar, D to D)

Test 1: uops

Code:

  fcvtms 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)0308191e3f4e51inst 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
1004303724003612547251000100010003981603018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372300282612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240001032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724000822547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms 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)03080b18191e1f3f4e51inst 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)9fa0a6a7a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000008429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000040071611611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830134
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001100071011611296330100001003003830038300383003830038
102043003723300000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000001012071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000100071011612296640100001003003830038300383003830038
1020430037233000054006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010167300373003711102011009910010010000100000000071011611296780100001003003830038300383003830038
10204300372330000306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000103071011611296330100001003003830038300383003830038
1020430229232010103528929547251011910010000100100005004277160130018300373003728264328762101002101000023210662304163003711102011009910010010000100000001126111011193233010235100001003059730709306583066130613

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3a3f4e51inst 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243008522500001242954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629110000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010200006402162229629010000103003830038300383003830038
100243003722400001032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722501200612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000121000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050428256813001830037300372828632876710010201000020100003022730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001830037302242828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372250000612954725100281010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms d0, d8
  fcvtms d1, d8
  fcvtms d2, d8
  fcvtms d3, d8
  fcvtms d4, d8
  fcvtms d5, d8
  fcvtms d6, d8
  fcvtms 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)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)9fa0a8a9acc5branch mispredict (cb)cdcfd6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000003111511816020036800001002004020040200402004020040
80204200391560302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391550302580108100800081008002050064078812002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391550582580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391563302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391550722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391556302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
80204200391553302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511816020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502019161311200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001040000502011161211200360080000102004020040200402004020040
80024200491560000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000050201116129200360080000102004020040200402004020040
800242003916100004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502012161213200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502013161311200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502011161113200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001000502013161212200360080000102004020040200402004020040
800242003915600004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000060502011161111200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502013161414200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502013161212200360080000102004020040200402004020040