Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (scalar, D)

Test 1: uops

Code:

  sqshl d0, d0, d1
  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)031e1f3f4e51inst 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)a0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371500621687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715300841687251000100010002646801201820372037157231895100010002000203720371110011000001073116121787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000000073116121787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000020073116121787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000000673116111787100020382038203820382038
1004203715150611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715270611687251000100010002646801201820372037157231895100010002000203720371110011000000073116121787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl d0, d0, d1
  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)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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204202651520145672440211319643119101791331004813410760680285409512019820276202271844027188371089421610664216203282027520280611020110099100100100001004180032824460221996225100001002026320182201842027520277
1020420275152005566044023681963210210191126100481291060868428538910201622003720278184402918817108892121083121821322202282022961102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000000010319687251010010010000100100005002847680020018200372003718422318745101002001000020020666200372003711102011009910010010000100000071011611197910100001002003820233200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500001906119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000000063319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000001206119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000074511611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

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)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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001001006402162219785010000102003820038200382003820038
1002420037150025511968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000006402162319785010000102003820038200382003820038
1002420037150121261968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000006402162319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715001831968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000006402162319785010000102003820038200382003820038
100242003715001241968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000606402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sqshl d0, d1, d0
  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)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
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037411020110099100100100001000000102008071011611197910100001002003820038200382003820038
1020420037150010000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000631196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000200320071011612197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720086111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371500000000536196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071023311197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403413319785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
100242003715000000053619687251001010100001010000502847680020018200372003718444318767100102010000202000020037201791110021109101010000100000006403163319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl d0, d8, d9
  sqshl d1, d8, d9
  sqshl d2, d8, d9
  sqshl d3, d8, d9
  sqshl d4, d8, d9
  sqshl d5, d8, d9
  sqshl d6, d8, d9
  sqshl d7, d8, d9
  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)03041e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420071150006125801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003815004924025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815001174025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920113200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150006325801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150104025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001003051101161120035800001002003920039200392003920039

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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502012161172003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050206166102003580000102003920039200392003920039
800242003815063925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502010161062003580000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010005020101610102003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050206161282003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050206166102003580000102003920039200392003920039
8002420038150041925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502010161062003580000102003920039200392003920039
800242003815001022580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100250206161062003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000502010166102003580000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010005020121610102003580000102003920039200392003920039