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, S to S)

Test 1: uops

Code:

  fcvtms 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)030b191e3f4e51inst 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
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110003073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037241006125472510001000100039816013018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
100430372301061254725100010001000398160030183037303724143289510001000100030373037111001100001273116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037240066125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110002073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms 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)03191e1f3a3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300007312954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043008423300001052954725101001001000010010000500427716003001803007630037282643287451010020010000200100003003730037111020110099100100100001002007101161129633100001003003830038300383003830038
1020430037234112007262954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003723300001242954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003723200001032954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003723300002752954725101001251001610010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007104161129633100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000037101161129633100001003003830038300383003830038
102043003723300001032954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161229633100001003003830038300383003830038
10204300372330000822954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000207101161129633100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233904702954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
10024300372321501052954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003723200612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037233006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101406403163329629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003723300822954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003723300612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037233002332954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629310000103003830038300383003830038
1002430037233008582954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010106403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms s0, s8
  fcvtms s1, s8
  fcvtms s2, s8
  fcvtms s3, s8
  fcvtms s4, s8
  fcvtms s5, s8
  fcvtms s6, s8
  fcvtms 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)03070a1e3f51inst 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)696b6d6edispatch 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
8020420061155110302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151182161120036800001002004020040200402004020040
80204200391551112302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391551103512580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110352580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000611151181161120036800001002004020040200402004020040
8020420039156110302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039156110722580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b18191e1f3a3f51inst 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)9fa6a7a8acdcache store miss (c0)c2cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051156000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201716813132019980000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000030050201716812132003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201616616122003680000102004020040200402004020040
80024200391550000000010325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201416616132003680000102004020040200402004020040
80024200391550000012004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000030050201716612122003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201616614132003680000102004020040200402004020040
80024200391550000000014525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201716618182003680000102004020040200402004020040
8002420039156000000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201116612122003680000102004020040200402004020040
8002420039156000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201516017142003680000102004020040200402004020040
8002420039155000000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000050201516017152003680000102004020040200402004020040