Apple M1 Microarchitecture Research by Dougall Johnson

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

UZP1 (vector, 8H)

Test 1: uops

Code:

  uzp1 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)03041e3a3f4e51inst 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
100420371600218016872510001000100026468002018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
10042037151028516872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
10042037161028516872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
10042037161027316872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
100420371610285168725100010001000264680020182037203715723189510001000200020372037111001100002477416441787100020382038203820382038
10042037161028516872510001000100026468012018203720371572318951000100020002037203711100110003077416441787100020382038203820382038
100420371610285168725100010001000264680120182037203715723189510001000200020372037111001100003977416441787100020382038203820382038
10042037150028516872510001000100026468012018203720371572318951000100020002037203711100110000377416441787100020382038203820382038
10042037161028516872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
10042037161028516872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038

Test 2: Latency 1->2

Code:

  uzp1 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)03080918191e1f3f4e51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000030071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037155000000251196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500003061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715600000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000003071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550010319687251001010100001010000882847680020018200372003718444318767100102010000202000020037200371110021109101010000100010640616221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100003640216221978510000102003820038200382003820038
1002420037156006119687251001010100001010000712847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371550953619687251001010100001110000552848963120018200372003718444318767100102010000202000020037200371110021109101010000102230640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010456612847680120018200372003718444318767100102010000202033820037200371110021109101010000100002035640224221978510000102003820038200382003820038
1002420037156006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715600157919687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100050640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100020640224221978510000102003820038200382003820038
1002420037155106119687251001010100001010000502847680120018200372008418444318786101652010000202000020037200371110021109101010000100003998640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp1 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)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)9fa1a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371551326421968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000710021611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100003710011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000710011611197910100001002003820038200382003820038
102042003715605361968725101001001000010010000500284768020018200372003718422718745101002001000020020000200372003711102011009910010010000100010710011611197910100001002003820038200382003820038
10204200371563611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100010710511611197916100001002008620132200382003820038
102042003715691031968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100001968710011611197910100001002003820038200382003820038
102042003715501031968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000710511611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000710011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100010710011611197910100001002003820038200382003820038
10204200371550611967625101001001000010010000500284768020018200372003718422818763101002041000020020000200372003711102011009910010010000100000710011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b181e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550200611968761100101010000101000050284768012001820037200841844431876710010201000020200002013120037111002110910101000010000640216221978510000102003820038200382008420038
10024200371550000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371550000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640224221978510000102003820038200382003820038
10024200371560000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371560000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371560000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371560000611968725100101010000101000050284768012001820037200371844431876710010201000022200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371550030611968725100101010000101000050284768002001820037200371845531876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp1 v0.8h, v8.8h, v9.8h
  uzp1 v1.8h, v8.8h, v9.8h
  uzp1 v2.8h, v8.8h, v9.8h
  uzp1 v3.8h, v8.8h, v9.8h
  uzp1 v4.8h, v8.8h, v9.8h
  uzp1 v5.8h, v8.8h, v9.8h
  uzp1 v6.8h, v8.8h, v9.8h
  uzp1 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)031e3f51inst 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)5e60696d6edispatch 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
8020420047156082258010010080000100800005006400000020019200382003899823999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
8020420038155340258010010080000100800005356400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038156040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038155040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101162120035800001002003920039200392003920039
8020420038155040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038155040258010010080000100800005006400000020019200382003899733999680100200800002001600002010020038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038155040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161220035800001002003920039200392003920039
80204200381550294258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815504962580100100800001008000050064000000200192003820038997339996801002008000020016000020038200381180201100991001008000010018051102161120035800001002003920039200392003920039
8020420038156040258010010080000100800005006400000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3a3f51inst 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)9fa1a7a8a9accficache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815500000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502003162320035080000102003920039200392003920039
8002420038161000120039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502003163220035080000102003920039200392003920039
8002420038155000000392580010108000010800005064000002001920038200389996271001880010208000020160000200382003811800211091010800001000400502003162320035080000102003920039200392003920039
800242003815500000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502002163220035080000102003920039200392003920039
800242003815500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000100502002163320035080000102003920039200392003920039
800242003815500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000502002163320035080000102003920039200392003920039
800242003815503100039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502034163320035080000102003920039200392003920039
800242003815600000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000502003163320035080000102003920039200392003920039
80024200381550000001021548029210802811380679506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502003163320035080000102003920039200392003920039
8002420038155000000392580010108000010800005064000012001920038200381000531001880010208000020160000200382003811800211091010800001000000502003162320035080000102003920039200392003920039