Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (scalar, D)

Test 1: uops

Code:

  uqshl 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)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
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000973116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110002073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl 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)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)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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500711968725101001001000010010000500284768012001820037200371842907187401010020010008200200162003720037111020110099100100100001000001117180160019802100001002003820038200382003820038
102042003715006311968725101001001000010010000500284768012001820037200371842907187401010020010008200200162003720037111020110099100100100001000201117170160019801100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500611968725101671001000010010000500284768012001820037200371842203187451010020010000200203362008620085111020110099100100100001000400007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000130007101161119791100001002003820038200382003820038
102042003715006221968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010003000007101161119791100001002003820038200382003820038
10204200371509611968725101001001000010010304500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001002000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000020006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028489630200182003720037184443187671001020100002020000200372003711100211091010100001000010006403163319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371846031876710010201000020200002003720037111002110910101000010000001206403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010306403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl 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)0308090b18191e1f3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000006119687251010010010000129100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500000000053619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100020071011611197910100001002003820038200382003820038
10204200371500000000010319687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e1f3a3f4e51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006404162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100280006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010040006402162219785010000102003820038200382003820038
100242003715000000536196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010080006402162219785010000102003820038200382003820038
1002420037150004140061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010070326402162219785010000102003820038200382003820038
10024200371490000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000061196874310010101000010100005028476802001820037200371845331876710010201000020200002003720037111002110910101000010000306402162219785010000102003820038200382003820038
100242003715000000631196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100110006402162219785010000102003820038200382003820038
10024200371500000061196876210010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl d0, d8, d9
  uqshl d1, d8, d9
  uqshl d2, d8, d9
  uqshl d3, d8, d9
  uqshl d4, d8, d9
  uqshl d5, d8, d9
  uqshl d6, d8, d9
  uqshl 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)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)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)9fa0a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150008225801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051104161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381500022725801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920087
8020420038150004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003821802011009910010080000100000000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
80204200381560082258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000046300051101161120035800001002003920039200392003920039
80204200381500017425801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019020038200389973399968010020080000200160000200382003811802011009910010080000100000000051101161120035800001002003920039200392003920039

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)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)9fa8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050201316322003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200316232003580000102003920039200392003920039
8002420038150041925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200216332003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050200316332003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050200316332003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050200316332003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899968100728001020800002016000020038200381180021109101080000100050200216332003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050200216232003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200316322003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100050200316332003580000102003920039200392003920039