Apple M1 Microarchitecture Research by Dougall Johnson

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

FACGT (vector, 8H)

Test 1: uops

Code:

  facgt v0.8h, v0.8h, v1.8h
  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)03181e3f4e51inst 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
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715096616872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037151048516872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150126116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150028516872510001000100026468012018203720371572318951000100020002037203711100110004973216221787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  facgt v0.8h, v0.8h, v1.8h
  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)030b1e1f3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500150611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715001805361968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007401161119791100001002003820038200382003820038
1020420037150060611968725101001001000011510152500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500150611968725101001001000010010000500284768012001820037200371842231881710100200100002002000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
10204200371510360611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
10204200371500270611968725101001001000010010000500284768012005420037200371842231874510100200100002002032820084200852110201100991001001000010042007101161119791100001002008620086200872003820038
1020420085150130611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150060611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000037101161119791100001002003820038200382003820038
102042003715001807181968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307090a0b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000030061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000006403162219785010000102003820038200382003820038
1002420037150000010240346196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000016402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200372110021109101010000100000006006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000001451968725100101010012101000050284768012001802003720037184443187671001020101802020000200372003711100211091010100001000004100006402162219785010000102003820038200382003820038
1002420037150000000399061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  facgt v0.8h, v1.8h, v0.8h
  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)03090b1e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000306119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003751102011009910010010000100007101161119791100001002003820038200382003820038
10204200371501106119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000098819687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500066119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa8c2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715024611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371503611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201065920200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371490611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715002501968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715001031968725100101010000101000050284768012001820037200371844431876710010201000020200002003720085111002110910101000010006402162219785010000102003820038200382003820038
100242003715039611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  facgt v0.8h, v8.8h, v9.8h
  facgt v1.8h, v8.8h, v9.8h
  facgt v2.8h, v8.8h, v9.8h
  facgt v3.8h, v8.8h, v9.8h
  facgt v4.8h, v8.8h, v9.8h
  facgt v5.8h, v8.8h, v9.8h
  facgt v6.8h, v8.8h, v9.8h
  facgt v7.8h, v8.8h, v9.8h
  movi v8.16b, 9
  movi v9.16b, 10

(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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491500000612580100100800001008000050064000012001920038200389973399968010020080000200160272200382003811802011009910010080000100230511041611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010019511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000012001920038200389973259996801002008000020016000020038200381180201100991001008000010030511011611200350800001002003920039200392003920039
802042003815000004025801001008000010180195500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000147511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010003511011611200350800001002003920039200392003920039
80204200381500000368258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010013511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200891180201100991001008000010020511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010013511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000138511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010048174511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8acc2cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500005142580010108000010800005064000020019020038200389996310018800102080000201600002003820038118002110910108000010012305020816064200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000200193200382003899963100188001020800002016000020038200381180021109101080000105005020716046200350080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019020038200389996310018800102080000201600002003820038118002110910108000010011405020416046200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000200190200382003899963100188001020800002016000020038200381180021109101080000104005020416066200350080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019020038200389996310018800102080000201600002003820038118002110910108000010010205020616056200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000200190200382003899963100188001020800002016000020038200381180021109101080000100005020616046200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000200190200382003899963100188001020800002016000020038200381180021109101080000100005020416046200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000200190200382003899963100188001020800002016000020038200381180022109101080000106905020716064200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000200190200382003899963100188001020800002016000020038200381180021109101080000101305020416067200350180000102003920039200392003920039
800242003815000039258001010800001080000506400002001902003820038999631001880010208000020160000200382003811800211091010800001007505020616064200350080000102003920039200392003920039