Apple M1 Microarchitecture Research by Dougall Johnson

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

USUBL2 (vector, 2D)

Test 1: uops

Code:

  usubl2 v0.2d, 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)03080a1e3f4e51inst 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)a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216321787100020382038203820382038
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  usubl2 v0.2d, 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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037156206119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101251119791100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371550010319687251010010010000100100005002848963120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371550012419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e203f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000022919687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640316221978510000102003820038200612003820038
100242003715600006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003714900006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150000072619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003716000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  usubl2 v0.2d, 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)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
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500003006119687251010010010000100100005002847680120018200372003718422318745101002081000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000036719687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000100071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640416331978510000102003820038200382003820038
1002420037156000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720078111002110910101000010010640316331978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768012001820037200371844431876710010201067020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010003640316331978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010010640316331978510000102003820038200382003820038
1002420037156000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
100242003715501201561968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037156000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037155000821968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  usubl2 v0.2d, v8.4s, v9.4s
  usubl2 v1.2d, v8.4s, v9.4s
  usubl2 v2.2d, v8.4s, v9.4s
  usubl2 v3.2d, v8.4s, v9.4s
  usubl2 v4.2d, v8.4s, v9.4s
  usubl2 v5.2d, v8.4s, v9.4s
  usubl2 v6.2d, v8.4s, v9.4s
  usubl2 v7.2d, 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)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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057156000351068258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021611200350800001002003920039200392003920039
80204200381560000040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381560000040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815600021040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042014115510072040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815500039040258010010080000100800005006400000200190200382003899733999680305200800002001600002003820038118020110099100100800001000000000511021611200350800001002003920039200392003920039
802042003815500039040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011612200350800001002003920039200392003920039
802042003815600015068258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000100511011611200350800001002003920039200392003920039
802042003815500075040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038155000189029258010810080008100800205006401320200190200382003899776998980100200800002001600002003820038118020110099100100800001000002000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080e1e3f51inst 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)9faccfd0d2d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155000392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100502000121601042003580000102003920039200392003920039
80024200381550003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020005160452003580000102003920039200392003920039
80024200381550003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020005160952003580000102003920039200392003920039
8002420038156000514258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010050200011160462003580000102003920039200392003920039
80024200381550003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020006160562003580000102003920039200392003920039
80024201101550003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001005020004160352003580000102003920039200392003920039
8002420038155000392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100502000101605112003580000102003920039200392003920039
800242003815500039258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010050200051601052003580000102003920039200392003920039
80024200381550006025800101080000108011250640000152001920038200389996031001880010208000020160000200382003811800211091010800001005020054160662003580000102003920039200392003920039
800242003815500039258001010800001080000506400001520019200382003899960310018804032080000201600002003820038118002110910108000010050205011160742003580000102003920039200392003920039