Apple M1 Microarchitecture Research by Dougall Johnson

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

UZP2 (vector, 16B)

Test 1: uops

Code:

  uzp2 v0.16b, v0.16b, v1.16b
  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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073216111787100020382038203820382038
100420371612105168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715082168725100010001000264680020182037203715723189510001000200020372037111001100000373116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000178073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037160251168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716082168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037160100168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uzp2 v0.16b, v0.16b, v1.16b
  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)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 ld/st (80)~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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371610611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011610197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715603381968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550891968725101001001000010010000500284768020018200372003718422318745101002001000020002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371600000124196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000101006616163319785010000102003820038200382003820038
10024200371610010166196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
10024200371610000717196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100016403163319785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
10024200371550000103196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000101006403163319785010000102003820038200382003820038
10024200371551000261196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785110000102003820038200382003820038
10024200371550000191196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715500012149196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100606403163319785010000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp2 v0.16b, v1.16b, v0.16b
  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)9fa0a1a6a8acc5cfd0d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715606119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372013211102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715536119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003751102011009910010010000100000000710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000100710011611197910100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100100640232221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037156006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371550015619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100100640216221978510000102003820038200382003820038
10024200371560010519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037156006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155036119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp2 v0.16b, v8.16b, v9.16b
  uzp2 v1.16b, v8.16b, v9.16b
  uzp2 v2.16b, v8.16b, v9.16b
  uzp2 v3.16b, v8.16b, v9.16b
  uzp2 v4.16b, v8.16b, v9.16b
  uzp2 v5.16b, v8.16b, v9.16b
  uzp2 v6.16b, v8.16b, v9.16b
  uzp2 v7.16b, v8.16b, v9.16b
  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)03080918191e1f3f51inst 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
80204200381550000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021611200350800001002003920087200392003920039
80204200381560000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011621200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100202800002001600002003820138118020110099100100800001000000000511011611200350800001002003920039200392003920039
802042003815500000011025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000001000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381560000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e3a3f51inst 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)9fa1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481551000190258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000090502005165320035080000102003920039200392003920039
8002420038155000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000200502005165320035080000102003920039200392003920039
8002420038155000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502004163520035080000102003920039200392009120039
8002420038155000039258001010800001080000506400002001920088200389996310018800102080000201600002003820038118002110910108000010000000502007163520035080000102003920039200392003920039
8002420038156000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010004000502008166620035080000102003920039200392003920039
8002420038156000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502005167520035080000102003920039200392003920039
800242003815500120392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020245165320035080000102003920039200392003920039
80024200381550000186425800101080000108000050640000200192003820038100303100188001020800002016000020038200381180021109101080000100000025020245163520035080000102003920039200392003920039
80024200381550000392580010108027810800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020243165420035080000102003920039200392003920039
80024200381560000392580010108000010800005064000020019200382003899963100188001020800002016000020090200901180021109101080000100000005020273165320035080000102003920039200392003920039