Apple M1 Microarchitecture Research by Dougall Johnson

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

SHADD (vector, 4S)

Test 1: uops

Code:

  shadd v0.4s, v0.4s, v1.4s
  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)a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073216111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111854100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715077168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  shadd v0.4s, v0.4s, v1.4s
  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)030b1e1f3a3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000001281968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011711197910100001002003820038200382003820038
1020420037150000012619687251012512510000125100006262847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979125100001002003820038200382003820038
102042003715000024461968725101001001000010010000500284768002001820037200371842231874410125200100002002000020037200371110201100991001001000010046071011611197910100001002003820038200382003820038
102042003715009002521968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000001451968725101001001000010010000500284768002001820228200371842231874510100200100002002000020037200371110201100991001001000010010071011633197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021611197910100001002003820038200382003820038
102042003715000001991968725101001001000010010000500284993312001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000631968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000001911968725101001001003610010000500284768002001820037200371842231874410125200100002002000020037200371110201100991001001000010000071021711197910100001002003820038200382003820038
102042003715000001031968725101001001000010010000500284768002001820037200371842231874410125200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080918191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000006311968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000001661968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  shadd v0.4s, v1.4s, v0.4s
  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)0308090b181e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000002761196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020210099100100100001000007102162219791100001002003820038200382003820038
1020420037150000023461196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000018611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000127102162219791100001002003820038200382003820038
102042003715000000232196872510100100100001001000050028476802005402003720037184223187451010020010000200200002003720037111020110099100100100001000207102162219823100001002003820038200382003820075
10204200371501111661196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371490000361196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000001861196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000000124196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038

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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715024061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006404163419785010000102003820038200382003820038
100242003715015082196872510010101000010100005028476800200182008520037184443187671001020101682020000200372003711100211091010100001000006404164319785010000102003820038200382003820038
1002420037150192061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006404164419785010000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006404163419785010000102003820038200382003820038
100242003715000532196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006404164319785010000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000120136404164319785010000102003820038200382003820038
10024200371509061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000106404163419785010000102003820038200382003820038
10024200371502288861196872510024121000010101526028476800200182003720037184443187671001020100002020000200372003711100211091010100001022006625323419785010000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000036404164419785010000102003820038200382003820038
100242003715039061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006404163419785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  shadd v0.4s, v8.4s, v9.4s
  shadd v1.4s, v8.4s, v9.4s
  shadd v2.4s, v8.4s, v9.4s
  shadd v3.4s, v8.4s, v9.4s
  shadd v4.4s, v8.4s, v9.4s
  shadd v5.4s, v8.4s, v9.4s
  shadd v6.4s, v8.4s, v9.4s
  shadd v7.4s, v8.4s, v9.4s
  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)031e1f3f51inst 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
8020420057150450402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051105161120035800001002003920039200392003920039
802042003815000822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051104161120035800001002003920039200392003920039
80204200381502940402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150120402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039

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)9fa0branch mispredict (cb)cfd5d6dadbddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715036039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050224160011200350080000102003920039200392003920039
80024200381503339258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050201161022200350080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001220800002016000020038200381180021109101080000100050201160011200350080000102003920039200392003920039
800242003815018939258001010800001080000506400000120019200382003899963100458001020800002016000020038200381180021109101080000100050201160011200350080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001220800002016000020038200381180021109101080000100050201160011200350080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050201160023200350080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050201160011200350080000102003920039200392003920039
80024200381501239258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050201160011200350080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050202160011200350080000102003920039200392003920039
8002420038150039258001210800001080000506400000120019200382003899963100188001220800002016000020038200381180021109101080000100050201160011200350080000102003920039200392003920039