Apple M1 Microarchitecture Research by Dougall Johnson

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

UMIN (vector, 8B)

Test 1: uops

Code:

  umin 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)a0a8a9acc3cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
1004203715306116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umin 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)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)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)9fa1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150218219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102052003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715036119687251010010010000100100005002847680020018200372003718422318818101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150053619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020091200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371502761196872510010101000010100005028476802012620037200371844431876710010201000020200002003720037111002110910101000010000640716221978510000102003820085200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500103196872510010101000010100005028476802001820037200371845131876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150361196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820083
1002420037150061196872510010101000010100005028476802001820084200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037156061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002520037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umin 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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371490061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150036361196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715002182196872510100102100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006619687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001013640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001010640216231978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001013640216221978510000102003820038200382003820038
10024200371490006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001010640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001010640216221978510000102003820038200382003820038
10024200371500006119687251001010100001210000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640316221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umin v0.8b, v8.8b, v9.8b
  umin v1.8b, v8.8b, v9.8b
  umin v2.8b, v8.8b, v9.8b
  umin v3.8b, v8.8b, v9.8b
  umin v4.8b, v8.8b, v9.8b
  umin v5.8b, v8.8b, v9.8b
  umin v6.8b, v8.8b, v9.8b
  umin 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)031e3a3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200481500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010013051104161120035800001002003920039200392003920039
802042003815000515258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040628010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010016051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010013051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010020051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010023051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090b18191e1f3a3f51inst 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)9fa0a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420059150000000000392580012108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010001060502004162320035080000102003920086200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000502001161120035080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100033000502001161120035080000102003920039200392003920039
8002420038150100000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000502001161120084080000102003920039200392003920039
8002420038150000000000392580012128000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000502001161120035080000102003920039200392003920039
80024200381500000000004425800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100021060502001161120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000502201161120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000502001161120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000502001161120035080000102003920039200392003920039
8002420038150000000000392580294108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010001000502001161120035080000102003920039200392003920039