Apple M1 Microarchitecture Research by Dougall Johnson

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

FACGE (scalar, S)

Test 1: uops

Code:

  facge s0, s0, s1
  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)03080b1e1f3f4e51inst 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
10042037150000611687251000100010002646802018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
10042037150000611687251000100010002646802018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371510003511687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715005106116872510001000100026468020182037203715723189510001000200020372037111001100013373116111787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100005173116111787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100001573116111787100020382038203820382038
10042037160000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716009027816872510001000100026468020182037203715723189510001000200020372037111001100001573116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  facge s0, s0, s1
  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)030b1e3f4e51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102161119791100001002003820038200382003820038
10204200371500321611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500360611968725101001001000010010000500284768002001820037200781842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001007101161119791100001002003820038200382003820038
102042008415000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820084
10204200371500309611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006404162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000021206402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000033006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000306402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119654431001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000208406402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000002306402162219785010000102003820038200382003820038
1002420037149000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000041306402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  facge s0, s1, s0
  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)031e1f3a3f4e51inst 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)9fa0a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768002001820037200371842961874110100200100082002001620037200371110201100991001001000010000007811171801600198010100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184297187411010020010008200200162003720037111020110099100100100001000010011171701600198020100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184296187401010020010008200200162003720037111020110099100100100001000000011171801600198010100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184296187411010020010008200200162003720037111020110099100100100001000000011171801600198010100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184297187411010020010008200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000013500071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000009600071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100096640216221978510000102003820038200382003820038
100242003715500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010243640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100069640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150002511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100093640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216331978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  facge s0, s8, s9
  facge s1, s8, s9
  facge s2, s8, s9
  facge s3, s8, s9
  facge s4, s8, s9
  facge s5, s8, s9
  facge s6, s8, s9
  facge s7, s8, s9
  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)030708091e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000003925801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000511051632200350800001002003920039200392003920039
802042003815010004025801251258000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011612200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001004803511012911200350800001002003920039200392003920039
8020420038150000013525801001008000010080000500640768020019200382003899730399968010020080000200160000200382003811802011009910010080000100006511011611200350800001002003920039200392003920039
8020420038150000012625801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000511211612200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000004025801001008000012580000626640000020019200382003899730399958012520080000200160000200382003811802011009910010080000100100511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100100511011611200350800001002003920039200392003920039
802042003815000004025801001008000012580000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a1a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500000000196258001010800001080000506400002001920038200389996310018800102080132201600002003820038118002110910108000010000000050205163520035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165520035080000102003920039200392003920039
80024200381500000721320190258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050203165520035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165620035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165320035080000102003920039200392003920039
80024200381500000000134258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000050205165320035080000102003920039200392003920039