Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAS (scalar, H to H)

Test 1: uops

Code:

  fcvtas h0, h0
  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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
10043037231261254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723961254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtas h0, h0
  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)0318191e1f3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100070071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100010071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100002671011611296330100001003003830038300383003830038
102043003722400006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000360371011611296330100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003724166129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003723906129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002210910101000010000640216222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640224222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037233053629547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003723206129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010100640216222962910000103003830038300383003830038
1002430037241071929547251002714100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010030640216222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730084111002110910101000010000640216222962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216332962910000103003830038300383003830038
100243003724106129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtas h0, h8
  fcvtas h1, h8
  fcvtas h2, h8
  fcvtas h3, h8
  fcvtas h4, h8
  fcvtas h5, h8
  fcvtas h6, h8
  fcvtas h7, h8
  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)0307080a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915600000000742580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000002000111511801600200360800001002004020040200402004020040
802042003916100000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111513401600200360800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
802042003915600000000302580108100800081028002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
8020420039155000000006952580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801600200360800001002004020040200402004020040
8020420039156000000001832580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801610200360800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001000111511801600200360800001002004020040200402004020040
802042003916100000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000200000111511801610200360800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801610200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3a3f5051inst 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)5f60696d6edispatch 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115500084025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000101350208164122003680000102004020111200402011420040
8002420039155000400258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502041612102003680000102004020040200402004020040
80024200391550004002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010405020616992003680000102004020040200402004020040
8002420039155000400258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001030502061611102003680000102004020040200402004020040
800242003915500040025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050207164112003680000102004020040200402004020040
80024200391550006102580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020516492003680000102004020040200402004020040
8002420039155000400258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502011161262003680000102004020040200402004020040
800242003915500040025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100350209161242003680000102004020040200402004020040
800242003915500040025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050205161152003680000102004020040200402004020040
80024200391550004002580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020616452003680000102004020040200402004020040