Apple M1 Microarchitecture Research by Dougall Johnson

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

UXTL (8H)

Test 1: uops

Code:

  uxtl v0.8h, v0.8b
  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)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
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371615611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037159611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uxtl v0.8h, v0.8b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

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)696d6edispatch 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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037156000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100001007101161119791100001002003820038200382003820038
1020420037156000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371551000120611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037155000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100010007101161119791100001002003820038200382003820038
1020420037155010000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550000120611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550000120611968625101001001000010010000500284752120018200372003718421318745101002001000020010182200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037155000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550000007261968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550000150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e5051inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150036119686025100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110901010100001000000640316221978610000102003820038200382003820038
1002420037150006119686025100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
10024200371500216119686025100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
10024200371500025119686025100101010000101000050284752112001820037200371844331876710010201000020101682003720037111002110901010100001000000640216221978610000102003820038200382003820038
1002420037150006119686025100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
1002420037150006119686025100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
1002420037150006119686025100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
1002420037150006119686025100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
10024200371500426119686025100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038
1002420037150006119686025100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110901010100001000000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uxtl v0.8h, v8.8b
  uxtl v1.8h, v8.8b
  uxtl v2.8h, v8.8b
  uxtl v3.8h, v8.8b
  uxtl v4.8h, v8.8b
  uxtl v5.8h, v8.8b
  uxtl v6.8h, v8.8b
  uxtl v7.8h, v8.8b
  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)03081e1f3f51inst 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
8020420059155090502580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181160020035800001002003920039200392003920039
8020420038155000522580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038155000712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038156000502580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001001011151180160020035800001002009120039200392003920039
8020420038156000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381560001562580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001001011151180160420045800001002003920039200392003920039
8020420038155000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160120035800001002003920039200392003920039
80204200381550003572580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381550003782580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038155000502580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)72scheduler 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)9fa0a1a6a8a9acc2cficache miss (d3)d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915600000000081258001010800001080000506400000200192003820038999603100188001020800002080000200382003811800211091010800001000000120502006165420035080000102003920039200392003920039
800242003815500000000081258001010800001080000506400000200192003820038999603100188001020800002080000200382003811800211091010800001000025000502004162420035080000102003920039200392003920039
800242003815501004553737401711122804771080464108049050643824020212202922029110038024101518049820804892080581202392028461800211091010800001002015225802510606804220229080000102029020298202872029220290
8002420296157010165672352025452580010108046512804865064308802025220291202901004502810180805002080490228000020038200381180021109101080000100000000502005164320035080000102019120241202402024220241
800242024415600005467244004178119805681080466108048650643178020220203352029010040026101538059220804872080585202902034361800211091010800001002214025880512204732520119080000102039020393203452033920388
800242037915700006680452812102158805741080559108068550645388020019200382003899960310018800102080000208000020038200381180021109101080000100000030510804685520229080000102024820344203422034120342
8002420391163201168531616036951788076210808451080780506454060203292024420446100440341006680204208068120802932039220242418002110910108000010000005880511102714420188080000102019120291201422038920190
800242033615620000012007552580010108009210800005064000002021720142203451001202610042805012080193208000020339203384180021109101080000104200025550502003162420035080000102003920039200392003920237
80024202451640001442675280123258001010800001080000506400000200192014020038999603100188001020800002080000200382003811800211091010800001022029014130506406972620157080000102054720191202912029220391
8002420038161000000300908258001010800001080000506400000200192003820038999603100188001020800002080000200382003811800211091010800001000023060502002164220035080000102003920039200392003920039