Apple M1 Microarchitecture Research by Dougall Johnson

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

UHADD (vector, 8B)

Test 1: uops

Code:

  uhadd v0.8b, v0.8b, v1.8b
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
100420371508216872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371508216872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uhadd v0.8b, v0.8b, v1.8b
  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)030408090b181e3f4e51inst 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)9fa1a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715000000186119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100010071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715000000010319687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038

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)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)9fa0a6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003714939061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500161196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001020000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150005361968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010002230640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000100640216221978510000102003820038200382003820038
100242003715000251196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uhadd v0.8b, v1.8b, v0.8b
  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)03191e3f4e51inst 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
1020420037150066119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500246119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371560018319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371490000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000010006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371501100000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000001035196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000094196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038201812003820038

Test 4: throughput

Count: 8

Code:

  uhadd v0.8b, v8.8b, v9.8b
  uhadd v1.8b, v8.8b, v9.8b
  uhadd v2.8b, v8.8b, v9.8b
  uhadd v3.8b, v8.8b, v9.8b
  uhadd v4.8b, v8.8b, v9.8b
  uhadd v5.8b, v8.8b, v9.8b
  uhadd v6.8b, v8.8b, v9.8b
  uhadd v7.8b, v8.8b, v9.8b
  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)03191e3a3f51inst 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)9fa0a1a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000012511031611200350800001002003920039200392003920039
8020420038149000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500005152580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)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)9fa1a6a8a9accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000392580010108000010800005064000012001932003820038999603100188001020800002016000020038200381180021109101080000100000050202160112003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100000050201160112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001902003820038999603100188001020800002016000020038200381180021109101080000100001050201160112003580000102003920039200392003920039
8002420038150003752580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100010050201160112003580000102003920039200392003920039
800242003815000612580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100000050201160112003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100000050202160222003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000102010050202160222003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100000050202160222003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100100050202160222003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001902003820038999603100188001020800002016000020038200381180021109101080000100000050201160112003580000102003920039200392003920039