Apple M1 Microarchitecture Research by Dougall Johnson

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

SRHADD (vector, 16B)

Test 1: uops

Code:

  srhadd 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)033f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371661168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000373116111787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371561168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  srhadd 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)03081e1f3f4e51inst 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
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037201331842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150030611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150030611968725101001001000010010000500284768002001820037200371842231874510259200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715005370611967625101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500150611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000006906119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006404162219785010000102003820038200382003820038
100242003715000001806119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000002406119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000035406119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000002406119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000001206119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  srhadd 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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371511290611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150210611968725101001001000010010000500284768020018200372003718422318745101622001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150210611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037149300611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150270611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371502761196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640316221978510000102003820038200382003820038
10024200371503061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371503061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001020000640216221978510000102003820038200382003820038
10024200371502461196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500126196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150264631196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  srhadd v0.16b, v8.16b, v9.16b
  srhadd v1.16b, v8.16b, v9.16b
  srhadd v2.16b, v8.16b, v9.16b
  srhadd v3.16b, v8.16b, v9.16b
  srhadd v4.16b, v8.16b, v9.16b
  srhadd v5.16b, v8.16b, v9.16b
  srhadd v6.16b, v8.16b, v9.16b
  srhadd 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)030a1e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381550014925801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100211110000511021611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000330000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500077925801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100500000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001002630000511011611200350800001002003920039202392003920039
80204200381500040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001001000000511011611200350800001002003920039200392003920039
8020420038149004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038153004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100002000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100200000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a1e3f51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500003925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010280905020216232003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001902003820038999631001880010208000020160000200382003811800211091010800001010005020316552003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001902003820038999631001880010208000020160000200382003811800211091010800001010305020316652003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010200605020316322003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001902003820038999631001880010208000020160000200382003811800211091010800001000005020216532003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001932003820038999631001880010208000020160000200382003811800211091010800001000005020216662003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019020038200381000531001880010208000020160000200382003811800211091010800001000005020316332003580000102003920039200392003920039
8002420038150006392580010108000010800005064000012001902003820038999631001880010208000020160000200382003811800211091010800001000905020616332003580000102003920039200392003920039
80024200381500003242580010108000010800005064000012001902003820038999631001880010208000020160000200382003811800211091010800001020605020316322003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001902003820038999631001880010208000020160000200382003811800211091010800001020305020216552003580000102003920039200392003920039