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, 8H)

Test 1: uops

Code:

  sshl v0.8h, v0.8h, v1.8h
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371536116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371508216872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715126116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715013916872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sshl v0.8h, v0.8h, v1.8h
  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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000004806119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000447061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000018071011611197910100001002003820038200382003820038
102042003715000009061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000039071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000001206119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000001206119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100020000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000906119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150001021968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001020640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
100242003715006611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001002032640416331978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640316431978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001832003720037184443187671001020100002020000200372003711100211091010100001000640316441978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sshl v0.8h, v1.8h, v0.8h
  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)03181e3f4e5051inst 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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968720021251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715009611968720021251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968720021251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150018611968720021251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150024251196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715005161196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000030061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184440318767100102010168202032620037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000082196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000120061196872510010101000010100005028476800200182003720037184440718767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000240061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000536196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sshl v0.8h, v8.8h, v9.8h
  sshl v1.8h, v8.8h, v9.8h
  sshl v2.8h, v8.8h, v9.8h
  sshl v3.8h, v8.8h, v9.8h
  sshl v4.8h, v8.8h, v9.8h
  sshl v5.8h, v8.8h, v9.8h
  sshl v6.8h, v8.8h, v9.8h
  sshl v7.8h, v8.8h, v9.8h
  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)03081e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815101840258010010080000100800005006400002001920091200389981399968010020080000200160000200382003811802011009910010080000100000051103161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500940258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa8accfd0icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500012392580010108000010800005064308402001920038200389996310018800102080000201600002003820038118002110910108000010005020001916000178200350080000102003920039200392003920039
8002420091150000102258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001003502000716000176200350080000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502000616000617200350080000102003920039200392003920039
800242003815000546392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020001716000617200350080000102003920039200392003920039
800242003815020396225800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200017160001717200350080000102003920039200392003920039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020001716000178200350080000102003920039200392003920039
800242003815000231392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020008160001717200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050220017160001717200350080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200017160001717200350080000102003920039200392003920039
80024200381501112392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020001716000817200350080000102003920039200392003920039