Apple M1 Microarchitecture Research by Dougall Johnson

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

USHL (vector, 4S)

Test 1: uops

Code:

  ushl v0.4s, v0.4s, v1.4s
  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)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
1004203718019016872510001000100026468012018203720371572318951000100020002037203711100110001373116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716126116872510001000100026468002018203720371572318951000100020002037203711100110000073116112034100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  ushl v0.4s, v0.4s, v1.4s
  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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715510000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715600000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715600000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500010006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000090017219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071014211197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680120018200372003718444251875510010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037160000000891968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037155000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037155000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037155000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037155000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037155000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371550000120611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037155000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010020000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  ushl v0.4s, v1.4s, v0.4s
  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)030b191e3f4e51inst 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)9fa8acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500276119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100200007101421119791100001002003820038200382003820038
10204200371551006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715500246119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371560006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371551006119687251010010010000100100005002847680120019200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371560006119687251010010010000100100005002847680120022200372003718422318745101002001000020020000200372003711102011009910010010000100000007101160119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680120018200372003718422718741101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006404243319785010000102003820038200382003820038
100242003715500061196872510010101000010100005028489630200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000516403163319785010000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715600089196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715500084196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715600061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200180200372003718444318767101602010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  ushl v0.4s, v8.4s, v9.4s
  ushl v1.4s, v8.4s, v9.4s
  ushl v2.4s, v8.4s, v9.4s
  ushl v3.4s, v8.4s, v9.4s
  ushl v4.4s, v8.4s, v9.4s
  ushl v5.4s, v8.4s, v9.4s
  ushl v6.4s, v8.4s, v9.4s
  ushl v7.4s, v8.4s, v9.4s
  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)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)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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102161120035800001002003920039200392003920039
802042003815500822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815600402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038155120402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100100051101161120035800001002003920039200392003920039
8020420038155150682580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815600402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815500402580100100800001008000050064000012001920038200859973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216112003580000102003920039200392003920039
8002420038155000679258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020116222003580000102003920039200392003920039
800242003815500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216112003580000102003920039200392003920039
800242003815500060258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000305020216222003580000102003920039200392003920039
800242003815500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216112003580000102003920039200392003920039
800242003815500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020116112003580000102003920039200392003920039
800242003815500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000305020116222003580000102003920039200392003920039
800242003815600039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216212003580000102003920039200392003920039
800242003815600039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020216112003580000102003920039200392003920039
800242003815500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005020116112003580000102003920039200392003920039