Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHR (vector, 8H)

Test 1: uops

Code:

  sshr v0.8h, v0.8h, #3
  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)03181e3f4e51inst 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)a0a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000003073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000006073216221786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000100073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000000073216221786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000003073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000013073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000000073216221786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshr v0.8h, v0.8h, #3
  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)03070b18191e1f3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000021419686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475210200182003720037184212518745101002001000020010000200372003711102011009910010010000100000071041622197910100001002003820038200382003820038
1020420037150000000124196862510100100100001001000050028475210200182003720037184213187451012520010000200100002003720037111020110099100100100001000000710416331979125100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521120018200372003718421318745101252001000020010000200372003711102011009910010010000100000071031622197910100001002003820038200382003820038
102042003714900000095619686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071041622197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071031622197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071031622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000103196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640516331978610000102003820038200382003820134
1002420037150000082196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038
10024200371500000726196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200180200372003718443718767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038
10024200371500001261196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640416331978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100010640416331978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshr v0.8h, v8.8h, #3
  sshr v1.8h, v8.8h, #3
  sshr v2.8h, v8.8h, #3
  sshr v3.8h, v8.8h, #3
  sshr v4.8h, v8.8h, #3
  sshr v5.8h, v8.8h, #3
  sshr v6.8h, v8.8h, #3
  sshr v7.8h, v8.8h, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

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)696d6edispatch 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715006292580108100800081008002050064013220019200382003899940699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815019292580108100800081008002050064013220019200382003899770699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220020200382003899770699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002004920049200492004920049
8020420049150006426801161008001610080028500640196200282004820049997601099868012820080038200800382004820048118020110099100100800001001022251281231120046800001002004920049200492004920050
8020420049150006427801161008001610080028500640196200282004920048997601099868012820080038200800382004820048118020110099100100800001000022251281231120045800001002004920050200502004920049
80204200481500037282680116100800161008002850064019620028200482004899760999868051920080038200800382004820048118020110099100100800001000022251291231120045800001002005020050200492004920050
8020420049150006426801161008001610080028500640196200282004820048997601099868012820080038200800382004820048118020110099100100800001000022251281231120046800001002005020049200492004920049
8020420048151006426801161008001610080028500640196200282004820048997601099868012820080038200800382004920048118020110099100100800001000022251291231120045800001002004920050200492004920050
8020420049150039922780116100800161008002850064019620028200492004899760999868012820080038200800382004820048118020110099100100800001000022251281231120045800001002004920049200492004920049
802042004815000642780116100800161008002850064019620028200482004899760999868012820080038200800382004820049118020110099100100800001000022251281231120045800001002004920049200492004920049

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)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)9faccfd2d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001005020010167820035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502009166420035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502008166520035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502007165520035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020136201042180021109101080000100502008166720035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502008168520035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502008167720035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502009168820035080000102003920039200882003920039
80024200381500123258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502008167620035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100502006165720035080000102003920039200392003920039