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, D)

Test 1: uops

Code:

  ushl 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)03081e3f4e51inst 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
1004203715008216872510001000100026468002018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
10042037150014816872510001000100026468012018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
10042037150010316872510001000100026468002018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
1004203716006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716006116872510001000100026468002018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
1004203716006116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  ushl 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)03181e1f3f4e51inst 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)9fa8accdcfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038
10204200371550002321968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038
1020420037156000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010003071011601119791100001002003820038200382003820038
1020420037156000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010010071011601119791100001002003820038200382003820038
10204200371550007261968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010010071011601119791100001002003820038200382003820038
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011601119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3a3f4e51inst 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
10024200371500000025119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000023219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010168202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444718767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  ushl 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)03070a18191e1f3f4e51inst 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)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155000100611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037156000000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371560000001731968725101001001000010010000500284768002001862003720037184229187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037155000000611968745101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000300071021622197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000011171711611198060100001002003820038200382003820038
1020420037156110000611968725101001001000010010000500284768002001802003720037184296187401010020010008200200162003720037111020110099100100100001000011171711611198060100001002003820038200382003820038
1020420037155110000611968725101001001000010010000500284768002001802003720037184296187401010020010008200200162003720037111020110099100100100001000011171811611198060100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070a0b18191e1f3f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200741551100015264611968725100101010000101060850284768002001820037200371844431876710316201000020200002003720037111002110910101000010030906402162219785010000102003820038200382003820038
100242003715510000300841968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006422162219785010000102003820038200382003820038
10024200371550000000921968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371550000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402163219787010000102003820038200382003820038
100242003715500000001671968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402166219785010000102003820038200382003820038
10024200371550000090611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371560000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371550000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371550000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715500000120611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219787010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  ushl d0, d8, d9
  ushl d1, d8, d9
  ushl d2, d8, d9
  ushl d3, d8, d9
  ushl d4, d8, d9
  ushl d5, d8, d9
  ushl d6, d8, d9
  ushl 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)03080b191e1f3f51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051103161120035800001002003920039200392003920039
80204200381550000024125801001008000010080000620640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003816100000974258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000018051101161120035800001002003920039200392003920039
8020420038155000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381550000040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000039051101161120035800001002003920039200392003920039
8020420038155000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038155000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392009020039
80204200381550126884025803061008000011480000500640000120019200382003899900399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381560000013525801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038155000004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100100051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030407080a0b1e3f51inst 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)9fabaccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155010000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020271624252003580000102003920039200392003920039
8002420038155020000392580010108000010800005064000002001920038200389996310045800102080000201600002003820038118002110910108000010005020221625252003580000102003920039200392003920039
8002420038155010000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020201625202003580000102003920039200392003920039
80024200381550100001792580010108010410800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020201626212003580000102003920039200392003920039
80024200381550200012392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020261627272003580000102003920039200392003920039
8002420038155010000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010035020261627272003580000102003920039200392003920039
80024200381550001012392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020271627272003580000102003920039200392003920039
8002420038155000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010035020251626292003580000102003920039200392003920039
8002420038155000009392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020211625182003580000102003920039200392003920039
8002420038155000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020271625272003580000102003920039200392003920039