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, 2D from 2D)

Test 1: uops

Code:

  scvtf 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)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
10043037230103254725100010001000398160130183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000273116112629100030383038303830383038
10043037231261254725100010001000398160030183037303724143289510001000100030373037111001100010073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230103254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100010073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf 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)03080b18191e3a3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000012010329547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
102043003722500000010329547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
1020430037225000012010329547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
1020430037225000012010329547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
1020430037225000012010329547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
102043003722500000010329547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000371011611296330100001003003830038300383003830038
102043003722500001206129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
1020430037225000012010329547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000371011611296330100001003003830038300383003830038
102043003722500001206129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010001371011611296330100001003003830038300383003830038
102043003722500000010329547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010001071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500001206129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100020006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100010006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000072629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100010306402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629110000103003830038300383003830038
10024300372250000308229547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100210006402162229629310000103022830370300853035630370
100243027222801571056176441295472510018101000010100006642800321301263037030132283071628916107622010653241081630415301319110021109101010000100060046402162229667410000103003830320303243018030229
1002430274227101810562646129547251001010100081410450604277160030018300373003728286828786106132010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf v0.2d, v8.2d
  scvtf v1.2d, v8.2d
  scvtf v2.2d, v8.2d
  scvtf v3.2d, v8.2d
  scvtf v4.2d, v8.2d
  scvtf v5.2d, v8.2d
  scvtf v6.2d, v8.2d
  scvtf 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)0308191e1f3f51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000016111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
8020420039150000060025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa0a1a7a8acc5cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000130502021622200365580000102004020040200402004020040
800242003915001282258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000130502041632200363580000102004020040200402004020040
800242003915001282258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010020200502021622200365880000102009120091200402004020040
80024200391500082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000000502021622200362180000102004020040200402004020040
80024200391500128225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000013050203163420036080000102004020040200402004020040
800242003915001282258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000100502021632200362180000102004020040200402004020040
800242003915001240258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000130502021622200362180000102004020040200402004020040
800242003915001282258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000160502021622200361680000102004020040200402004020040
8002420039150008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000010050202162220036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000013050203163320036080000102004020040200402004020040