Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (vector, 4S)

Test 1: uops

Code:

  uqshl 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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020852038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715019716872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371536116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038207420862038

Test 2: Latency 1->2

Code:

  uqshl 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)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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371560000902351968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000300071011611197910100001002003820038200382003820038
10204200371550000001611967643101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100002070071011611197910100001002003820038200382003820038
10204200371500000002161968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003721102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768020018200372003718422318745102752001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100200000071011611197910100001002003820038200382003820038
1020420037151000000611967625101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000001031968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200862003820038
1020420037150100000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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)6061696d6edispatch 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003716700233196872510010101000010100005028476800020018200372003718444031876710010201000020200002003720037111002110910101000010006400416221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801020018200372003718448031876710010201000020200002003720037111002110910101000010006400216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801020018200372003718444031876710010201000020200002003720037111002110910101000010006400216221978510000102003820038200382003820038
10024200371500082196872510010101000010100005028476800020018200372003718444031876710010201000020200002003720037111002110910101000010036400216221978510000102003820038200382003820038
100242003715090170196872510010101000010100005028476800020018200372003718444031876710010201000020200002003720037111002110910101000010006400216221978510000102003820038200382003820038
10024200371502101931968725100101210000101000050284768000200182003720037184440161876710010201000020200002003720037311002110910101000010006400216221978510000102003820038200382003820086
100242003715001124196872510010101000012100005028476800020018200372003718444031876710010201000020200002003720179111002110910101000010396400216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800020018200372003718444031876710010201000020200002003720037111002110910101000010006400216221978510000102003820038200382003820038
100242003715000170196872510010101000010100005028476801020018200372003718444031876710010201000020200002003720037111002110910101000010036400216221978510000102003820038200382003820038
100242003715012061196872510010101000010100005028476800020018200372003718444031876710010201000020200002003720037111002110910101000010006400216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl 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)03070918191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150100000277196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000084196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
1020420037150000000424196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000084196872510138100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000084196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021722197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038
102042003715000000082196762510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000014919687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000014519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444718767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000018919687251001010100001010000502851529120018200372003718444818767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000016619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003714900018719687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785210000102003820038200382003820038
100242003715000021219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100306402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl v0.4s, v8.4s, v9.4s
  uqshl v1.4s, v8.4s, v9.4s
  uqshl v2.4s, v8.4s, v9.4s
  uqshl v3.4s, v8.4s, v9.4s
  uqshl v4.4s, v8.4s, v9.4s
  uqshl v5.4s, v8.4s, v9.4s
  uqshl v6.4s, v8.4s, v9.4s
  uqshl 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)030b1e3f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004715000612580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511031614200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920100200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150001492580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802052003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020316332003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020216322003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020216322003580000102003920039200392003920039
8002420038150022925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020316332003580000102003920039200392003920039
80024200381500107125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020316322003580000102003920039200392003920039
800242003815003925800101080000108000050640000200672003820038999631001880010208000020160000200382003811800211091010800001005020316332003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020316322003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200872003811800211091010800001005020216232003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020316322003580000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020216232003580000102003920039200392003920039