Apple M1 Microarchitecture Research by Dougall Johnson

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

ORR (vector, 8B)

Test 1: uops

Code:

  orr v0.8b, v0.8b, v1.8b
  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)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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150139168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037208515723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  orr v0.8b, v0.8b, v1.8b
  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)03080b1e1f3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000001052196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000901196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500090166196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382008620038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100028037101161119791100001002003820038200382003820038
102042003715000001048196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000991196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100022037101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000733196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100003640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715001279219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000102000640216221978510000102003820038200382003820038
1002420037150066119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100070640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  orr v0.8b, v1.8b, 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)03081e3f4e51inst 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)9fa6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500084196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010001030071011611197910100001002003820038200382003820038
102042003715000453196872510100100100001001000050028476802001820037200371842231874510100200101782002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150001031968725101001031000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000120071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000346196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010001030071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e1f3f4e51inst 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
10024200371550000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000010961968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402163319785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102013420038200382003820038
100242003715000007261968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  orr v0.8b, v8.8b, v9.8b
  orr v1.8b, v8.8b, v9.8b
  orr v2.8b, v8.8b, v9.8b
  orr v3.8b, v8.8b, v9.8b
  orr v4.8b, v8.8b, v9.8b
  orr v5.8b, v8.8b, v9.8b
  orr v6.8b, v8.8b, v9.8b
  orr v7.8b, v8.8b, v9.8b
  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)0308090b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021611200350800001002003920039200392003920039
8020420038150000000012425801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038150000000010325801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000511324025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000001000511011611200350800001002003920039200392003920039
8020420038150000000018925801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038150000000016825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021621200350800001002003920039200392003920039
8020420038149000000012425801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)5f60696d6edispatch 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)9fa8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050201616017142003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020171609172003580000102003920039200392003920039
80024200381500131258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050201416014152003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800982016000020038200381180021109101080000100050201416016142003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050201516017172003580000102003920039200392003920039
8002420038150016725800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020181601782003580000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050201516010172003580000102003920039200392003920039
80024200381500125258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050201616017172003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016019820088200381180021109101080000100050201716016182003580000102003920039200392003920039
8002420099150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050201316017142003580000102003920039200392003920039