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, 8H)

Test 1: uops

Code:

  uqshl 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)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
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371536116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl 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)03091e3f4e51inst 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)9fa8a9accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150068219687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
102042003715004746119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500336119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150066119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150036119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150006119687251010010410000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038
10204200371500276119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03071e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150025261196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
100242003715016611968725100101010000101000050284768020018200372003718444201876710012201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064241622197850010000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
100242003715005761196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002210910101000010000364221622197850010000102003820038200382003820038
100242003715003061196872510010121000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
1002420037150015536196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
10024200371560061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038
100242003715001561196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000064021622197850010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uqshl 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)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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371503672619687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
1020420037150010519687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002007120038200382003820038
10204200371501844119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119832000100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791000100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371590003060611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500002406119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200374110021109101010000100112640216221978510000102003820038200382003820038
100242003715010000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037211002110910101000010000640225221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010400640316221978510000102003820038200382003820038
100242003715000030611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371610101071179241861959915510060121009614106046028553780203062022720462184673918878107743211498222262220417203691011002110910101000010000640216221978510000102003820038200382003820038
100242003715500000611968725100101010000101000050284768002001820037201791844481876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uqshl v0.8h, v8.8h, v9.8h
  uqshl v1.8h, v8.8h, v9.8h
  uqshl v2.8h, v8.8h, v9.8h
  uqshl v3.8h, v8.8h, v9.8h
  uqshl v4.8h, v8.8h, v9.8h
  uqshl v5.8h, v8.8h, v9.8h
  uqshl v6.8h, v8.8h, v9.8h
  uqshl 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)030818191e1f3f51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820110118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038150000210402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003814900000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500001590402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa1a6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715003639258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050208167122003580000102003920039200392003920039
8002420038150033925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100205020121610122003580000102003920039200392003920039
8002420038150006025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020131612132003580000102003920039200392003920039
80024200381500070425800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020151613132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020121611142003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000502011168122003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020131613122003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502011169112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020101613112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020131613112003580000102003920039200392003920039