Apple M1 Microarchitecture Research by Dougall Johnson

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

SHSUB (vector, 16B)

Test 1: uops

Code:

  shsub v0.16b, v0.16b, v1.16b
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371608416872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000673116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  shsub v0.16b, v0.16b, v1.16b
  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)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)9facbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715003611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042008415000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000106640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372022618444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500103196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001021640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715008219667251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150072619687251001010100001010000502847680120018200372022718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  shsub v0.16b, v1.16b, v0.16b
  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)030818191e1f3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382008520038
10204200371500000034619687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200872008720038
102042003715500000114819687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010001071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038201792003820038
1020420037149000006119687251010010010000100100005002847680120018020037200371842231874510100200100002042000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090a0b18191e1f3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403164319785010000102003820038200382003820038
10024200371500000000089519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402163419785010000102003820038200382003820038
10024200371500000000056719687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000000036019687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000000045019687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785210000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444618767100102010000202000020037200371110021109101010000100001306403163319785010000102003820038200382003820038
10024200371501000009906119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000306403163319785010000102003820038200382003820038
10024200371500000001808419687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
1002420037150000000008219687251001010100001010000502847680120018200372003718444318767100102210000202000020037200371110021109101010000100001006403163319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  shsub v0.16b, v8.16b, v9.16b
  shsub v1.16b, v8.16b, v9.16b
  shsub v2.16b, v8.16b, v9.16b
  shsub v3.16b, v8.16b, v9.16b
  shsub v4.16b, v8.16b, v9.16b
  shsub v5.16b, v8.16b, v9.16b
  shsub v6.16b, v8.16b, v9.16b
  shsub v7.16b, v8.16b, v9.16b
  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)0307090a181e1f3a3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815010100022232580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511491677200350800001002003920039200392003920039
802042003815010110024725801001008000010080000500640000020019200382003899732099968010020080000200160000200382003811802011009910010080000100000511441699200358800001002014020529202462013820281
80204200381501010002472580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511491677200350800001002003920039200392003920039
802042003815010101202472580100100800001008000050064000002001920038200389973399968010020080000200160198200382003811802011009910010080000100000511491699200350800001002003920039200392003920039
80204200381501010002472580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511491699200350800001002003920039200392003920039
80204200381501010002472580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100031498511493249200350800001002003920039200392003920039
80204200381501110002472580100100800001008000050064076402001920038200389973399968010020080000200160000200382003811802011009910010080000100003511491699200350800001002003920039200392003920039
80204200381501010002472580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511441699200350800001002003920039200392003920039
80204200381501010002472580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511491699200350800001002003920039200392003920039
80204200381501010002472580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511491699200350800001002003920039200392003920039

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)6061696d6edispatch 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)9fa1accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915100392580010108000010800005064000004200192003820038999631001880010208000020160000200382003811800211091010800001000502005162220035080000102003920039200392003920039
800242003815000452580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162220035080000102003920039200392003920039
800242003815000392580010108000011800005664000000200192003820038999631001880010208000020160000200382003811800211091010800001000502003162220035080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162220035080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162220035080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162220035080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502003162220035080000102003920039200392003920039
800242003815010392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004163320035080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162220035080000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502004162220035080000102003920039200392003920039