Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (vector, integer, 2S from 2S)

Test 1: uops

Code:

  scvtf v0.2s, v0.2s
  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
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100017073116112629100030383038303830383038
1004303723040625472510001000100039816013018303730372414328951000100010003037303721100110000073116112629100030383038303830383038
1004303722126125472510001000100039816013018303730372414328951000100010003037303711100110008073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110009373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100010373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110005073116112629100030383038303830383038
1004303722126125472510001000100039816003018303730372414328951000100010003037303711100110003373116112629100030383038303830383038
10043037231261254725100010001000398160030183037303724143289510001000100030373037111001100021073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100010073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf v0.2s, v0.2s
  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)031e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250103295472510100100100001001000050042771601300183003730037282643287451027220010000200100003003730037411020110099100100100001003607101161129633100001003003830038300383003830038
102043003722512103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001307101161129633100001003003830038300383003830038
102043003722512103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003008430037111020110099100100100001000307101161129633100001003003830038300383003830038
10204300372250103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001007101161129633100001003003830038300383003830038
10204300372250103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001307101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001307101161129633100001003003830038300383003830038
102043003722512103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001307101161129633100001003003830038300383003830038
10204300372250768295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001007101161129633100001003003830038300383003830038
102043003722512103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001307101161129633100001003003830038300383003830038
10204300372251261295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000307101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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 ld/st (80)~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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500010000536329466171100801210048161135067428797613027030417304132833439289191076324113242401097830461304511011002110910101000010000122491308275883529982310000103027430416304613045330371
1002430452232111981212880058572946617310079131006415113506042879760303423046530459282994028938113622411458200106553055430512101100211091010100001000010306402162229667010000103031430462302283027430134
1002430320229111271188352068629547251001913100081010000664283920030162301303045228313412882410312201066922011147303213031981100211091010100001000000348083484229917210000103041630275302253003830038
1002430037225000002100518829493981007913100641110300724282568030018300373003728286328767100102010163200100003003730037111002110910101000010222022250506402162229629010000103027630320305083027630273
100243046523501067795704157272954725100101010000101000050427716003030630131301322828624289171001020100002031810000300373003711100211091010100001000010306402162229629010000103003830038300383003830038
100243003723200000000612954725100101010000101000050427716013001830037300372828632876710010201000020010000300373003711100211091010100001000010006402162229629010000103003830038300383003830038
100243003722400000000612954725100101010000101000050427716003001830037300372828632876710010201000020010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000000001452954725100101010000101000050427716003001830037300372828632876710010201000020010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716013001830037300372828632876710010201000020010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372330000039004762954725100101010000101000050427716013001830037300372828632876710010201000020010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf v0.2s, v8.2s
  scvtf v1.2s, v8.2s
  scvtf v2.2s, v8.2s
  scvtf v3.2s, v8.2s
  scvtf v4.2s, v8.2s
  scvtf v5.2s, v8.2s
  scvtf v6.2s, v8.2s
  scvtf v7.2s, v8.2s
  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)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
80204200581501112302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040
80204200391501112302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
80204200391501112722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040
8020420039150110722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020091200402004020040
80204200391501131602580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
80204200391501112722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040
80204200391501136722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040
80204200391501112722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011125472580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
80204200391501112722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e1f3f51inst 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)9fa7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500908225800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020151612162003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020141615162003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020151614112003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020121616132003680000102004020040200402004020040
8002420039150000102725800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001002005020131613162003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020141616132003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020141616132003680000102004020040200402004020040
8002420039150000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000502011169142003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020151613132003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020161616122003680000102004020040200402004020040