Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHL (vector, 16B)

Test 1: uops

Code:

  sshl v0.16b, v0.16b, v1.16b
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037159061168725100010001000264680020182037203715723189510001000200020372037111001100003373116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150061168725100010001000264680020182037203715723189510001000200020372037111001100001873116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sshl v0.16b, v0.16b, v1.16b
  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)030b18191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715001000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100020071021611197910100001002003820038200382003820038
1020420037150000007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
1020420037150000001031968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372008411102011009910010010000100070071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001016520020000200372003711102011009910010010000100060071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100020071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100070071011611197910100001002003820038200382003820038
10204200371500001560611968725101001001000010010000500284768020018200372003718422318763101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
1020420037150100006119687251010010010000129100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000370071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768020018200852003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
1020420037150000120611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100012371011611197910100001002003820038200382003820038

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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500536196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200372110021109101010000100000640416441978510000102003820038200382003820038
1002420037150061196432510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640316341978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640416431978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640316431978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640416441978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640416341978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000105001640416431978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110022109101010000101000640316341978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000105000640416431978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640416441978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sshl v0.16b, v1.16b, v0.16b
  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)03040b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715010000061196872510100100100001001000050028476800200182003720037184297187401010020010008200200162003720037111020110099100100100001000000003011171701600198010100001002003820038200382003820038
102042003715000000066196872510100100100001001000050028476800200182003720037184296187411010020010008200200162003720037111020110099100100100001000000000011171801600198010100001002003820038200382003820038
102042003715100000061196872510100100100001001015050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000006000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000000071011611197910100001002003820038200382003820038
102042003714900000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000006000071011611197910100001002003820038200382003820038
1020420037150000000536196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001301000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000003000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e3f4e51inst 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)9fa1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100010006402162219785010000102003820038200382003820038
10024200371490006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444718786100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371501006119687251001010100241010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100010006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100002306402164219785010000102003820038200382003820038
100242003715000126119687431002412100121010000502847680020054200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502848963020018200372003718444318783101622010000202000020037200371110021109101010000100000203306402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000306402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000306402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sshl v0.16b, v8.16b, v9.16b
  sshl v1.16b, v8.16b, v9.16b
  sshl v2.16b, v8.16b, v9.16b
  sshl v3.16b, v8.16b, v9.16b
  sshl v4.16b, v8.16b, v9.16b
  sshl v5.16b, v8.16b, v9.16b
  sshl v6.16b, v8.16b, v9.16b
  sshl v7.16b, v8.16b, v9.16b
  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)031e3a3f51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150024125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000060511412169920035800001002003920039200392003920039
80204200381500241258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051141052121120035800001002003920039200392003920039
80204200381500241258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000185114101610920035800001002003920039200392003920039
802042003815002412580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511491610920035800001002003920039200392003920039
802042003815002412580100100800001008000050064000020019200382003899733999680319200800002001600002003820038118020110099100100800001000000511491691020035800001002003920039200392003920039
80204200381500241258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051149169920035800001002003920039200392003920039
8020420038150024125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000005114101610920035800001002003920039200392003920039
8020420038150024125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000063511491610920035800001002003920039200392003920039
80204200381500241258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000455114916101120035800001002003920039200392003920039
80205200381500241258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051141016101120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a0b18191e1f3a3f51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000102005020121613920035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201316131020035080000102003920039200392003920039
80024200381500000000392580086108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502081681320035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502081691220035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020131691220035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020131612820035080000102009820039200392003920039
800242003815000005700392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502081681320035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020121691220035080000102003920039200392003920039
8002420038150000000070425800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020121612820089380000102009120092200912013720090
80024200881501122264192132361801041280095128009855640768020065200922008810014710018800102080000201600002003820038118002110910108000010013502081691320035080000102003920039200392003920039