Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINP (vector, 8B)

Test 1: uops

Code:

  uminp 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)030b1e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110006073116111787100020382038203820382038
100420371600611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uminp 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)03090b181e1f3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500002010611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500003570611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500005760611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000150611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500005700611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000450611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500004620611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500001501031968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000003071011611197910100001002003820038200382003820038

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)9fa8acbranch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715033611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006400516331978510000102003820038200382003820038
1002420037150264611968725100101010000101000055284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038
1002420037150378611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038
100242003715024611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038
1002420037150331171968725100101010000101000050284768005200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038
100242003715027611968725100101010000101000050284768010200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038
1002420037150456611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372013221100211091010100001000006400316331978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006405316331978510000102003820038200382003820038
100242003715015611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038
100242003715030611968725100101010000101000050284768000200182003720037184443187671001020100002020000200372003711100211091010100001000006400316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uminp 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)03081e3f4e51inst 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)9fa8c2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500336119687251010010010000100100005002847680120018200372003718429718741101002001000820020016200372003711102011009910010010000100001117180160019801100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718429618741101002001000820020016200372003711102011009910010010000100001117180160019801100001002003820038200382003820038
1020420037150096119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500072619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000017101160119791100001002003820038200382003820038
10204200371500186119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100300007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006666119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000240061196872510010101000010100005028476801520018200372003718444318767100102010000202000020037200371110021109101010000100000000064052162219785010000102003820038200382003820038
1002420037150000000000726196872510010101000010100005028476801520018200372003718444318767100102010000202000020037200371110021109101010000100000000066752162219785010000102003820038200382003820038
100242003715000000000061196872510010101000010100005028476801520018200372003718444318767100102010000202000020037200371110021109101010000100000000064002162219785010000102003820038200382003820038
100242003715000000030061196872510010121000010100005028476801520018200372003718444318767100102010000202000020037200371110021109101010000100000000064053162219785010000102003820038200382003820038
100242003715000000000061196872510010101000010100005028476801520018200372003718444318767100122010000202000020037200371110021109101010000100000000064052162219787010000102003820038200382003820038
1002420037150000000510061196872510010101000010100005028476800520018200372003718444318767100102010000202000020037200371110021109101010000100000000064052162219785010000102003820038200382003820038
100242003715000000000061196872510010101000010100005028476801020018200372003718444318767100122010000202000020037200371110021109101010000100000000064002162219785010000102003820038200382003820038
1002420037150000000240061196872510010101000012100005028476801520018200372003718444318767100102010000202000020037200371110021109101010000100000000064002162219785010000102003820038200382003820038
100242003715000000000061196872510010101000010100005028476801520018200372003718444318767100102010000202000020037200371110021109101010000100000000064002162119785010000102003820038200382003820038
100242003715000000000061196872510010101000010100005028476800520018200372003718444318767100102010000202000020037200371110021109101010000100000000064002162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uminp v0.8b, v8.8b, v9.8b
  uminp v1.8b, v8.8b, v9.8b
  uminp v2.8b, v8.8b, v9.8b
  uminp v3.8b, v8.8b, v9.8b
  uminp v4.8b, v8.8b, v9.8b
  uminp v5.8b, v8.8b, v9.8b
  uminp v6.8b, v8.8b, v9.8b
  uminp 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)030b18191e3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000040258020010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038149000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815000004025801001008000010080000500640000200192003820038997339996802062008009620016000020038200381180201100991001008000010047551101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a181e1f3a3f51inst 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)9fa0a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715011030246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000150241816161620035080000102008820039200392003920039
800242003815511000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241616161620035080000102003920039200392003920039
8002420038150110002141258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241316171320035080000102003920039200392003920039
800242003814911000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241616151620035080000102003920039200392003920039
800242003815011000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241516151620035080000102003920039200392003920039
800242003815011000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241816161320035080000102003920039200392003920039
800242003815011000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241616181720035080000102003920039200392003920039
800242003815011000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241616181620035080000102003920039200392003920039
80024200381501100024625800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000005024171681720035080000102003920039200392003920039
800242003815011000246258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050241616151720035080000102003920039200392003920039