Apple M1 Microarchitecture Research by Dougall Johnson

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

UMAXP (vector, 8H)

Test 1: uops

Code:

  umaxp 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)03181e1f3f4e51inst 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
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
10042037150008216872510001000100026468002018203720371572318951000100020002037203711100110000973116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000973116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000673116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umaxp 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)0318191e1f3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000003071021622197910100001002003820038200382003820038
102042003715000006119687251010010010036100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000010071021622197910100001002003820038200382003820038
1020420037150000025119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000006119687981010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000020071021622197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000003071021622197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038

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)6061696d6edispatch 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715506119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
1002420037150044119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801120018200372003718444318767100102010000202000020037200371110021109101010000104306401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010036401216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680112001820037200371844431876710010201000020200002003720037111002110910101000010006400216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umaxp 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)03191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001001007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000027102242219791100001002003820038200382003820038
10204200371500010461196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150012061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715001206119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100012007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100481001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038

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)6061696d6edispatch 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)9fa8accdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196652510010121000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100006400216221978510000102003820038200382003820038
100242003715001032196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100006400216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100006400216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010012006400216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100006400216221978510000102003820038200382003820038
10024200371499948196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000102006400216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010011406400216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200841110021109101010000100006400216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100006400216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100006400216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umaxp v0.8h, v8.8h, v9.8h
  umaxp v1.8h, v8.8h, v9.8h
  umaxp v2.8h, v8.8h, v9.8h
  umaxp v3.8h, v8.8h, v9.8h
  umaxp v4.8h, v8.8h, v9.8h
  umaxp v5.8h, v8.8h, v9.8h
  umaxp v6.8h, v8.8h, v9.8h
  umaxp 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)03073f51inst 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
802042003815004025801001008000010080000626640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100011451101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000351101161120035800001002003920039200392003920039
802042003815004025801001008000012580000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815008225801001008000012580000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a0b18191e1f3f51inst 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)9fa1a6a7a8a9acc2branch mispredict (cb)cfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000000010225800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502091608920035080000102003920039200392003920039
80024200381500000000010425800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502061607620035080000102003920039200392003920039
800242003815000000000125258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005020816071120035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502091608820035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000010000502081606720035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000020300502081608620035080000102003920039200392009020039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000471005054111606820035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200381000531004580010208000020160000200382003811800211091010800001000100000502091609720035080000102003920039200392003920039
80024200381500000001203925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502071606920035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502061607820035080000102003920039200392003920039