Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (immediate, vector, 8B)

Test 1: uops

Code:

  uqshl v0.8b, v0.8b, #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)03071e3f4e51inst 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)a8acc2cfd5d6daddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000732160221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000733160221786100020382038203820382038
100420371510611686251000100010002645210201820372037157131895100010001000203720371110011000000733160221786100020382038203820382038
100420371510611686251000100010002645210201820372037157031914100010001000203720371110011000000732160221786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000000732160321786100020382038203820382038
1004203715001551686251000100010002645210201820372037157131895100010001000203720371110011000000733160221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000732160221786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000732160221786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000000732160221786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000000732160331786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl v0.8b, v0.8b, #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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968610110100122100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000830196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000284196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184250318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100100000071011611197910100001002003820038200382003820038
1020420037150000060061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000003071011611197910100001002003820038200382003820038
1020420084150000090061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100000000071021611197910100001002003820038200382003820038

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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150014519686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715008419686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150126119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150053619686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216421978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

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

(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)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)9fa6a8a9c2c5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150240292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
80204200381502941322192580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151351620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039
802042003815000962580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151181620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000000060102258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000010305020000116000112003500080000102003920039200392003920039
800242003815000000021039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
80024200381500000009039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
800242003815000000024039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
800242003815000000090039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
800242003815000000018039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
8002420038150000000210704258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
800242003815000000036039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039
800242003815000000042039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020000116000112003500080000102003920039200392003920039