Apple M1 Microarchitecture Research by Dougall Johnson

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

USHL (vector, 2S)

Test 1: uops

Code:

  ushl v0.2s, v0.2s, v1.2s
  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)a6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371706116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371608416872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  ushl v0.2s, v0.2s, v1.2s
  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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021611197910100001002003820038200382003820038
10204200371550441196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710116111979117100001002003820038200382003820038
1020420037155061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037155061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037155061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037156661196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000300071011611197910100001002003820038200382003820038
1020420037155061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371610103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371560131196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

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)9fa0a6a8acbccdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006406165519785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006405165519785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006406164419785010000102003820038200382003820038
10024200371500025119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006405166519785010000102003820038200382003820038
1002420037155008919687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006404164619785010000102003820038200382003820086
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006405165519785010000102003820038200382008520038
100242003715002761196872510010101000010100005028476801200182003720037184441418767100102010000202000020037200371110021109101010000100000006405166519785010000102003820038200382003820038
100242003715004416119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006405165519785010000102003820038200382003820038
100242003715004326119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006405164519785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006405165519785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  ushl v0.2s, v1.2s, v0.2s
  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)0308191e3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000006973531622197910100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372008518422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371560006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037155000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000015071021622197910100001002003820038200382003820038
1020420037155001596119687251010013510000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100200595171021722197910100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371551006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820087
10204200371550008219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa1a6a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037149006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680002001820037200371845931876710160201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038
1002420037150606119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680002001820037200371844831876710010201000020200002003720037111002110910101000010020064000216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102008620086200852008520038
10024200831501328857619687251001010100001010000502847680102001820037200371844431876710010201000020200002008320085211002110910101000010400066200216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502850246002001820037200371844431876710010201000020200002003720037111002110910101000010000064000216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  ushl v0.2s, v8.2s, v9.2s
  ushl v1.2s, v8.2s, v9.2s
  ushl v2.2s, v8.2s, v9.2s
  ushl v3.2s, v8.2s, v9.2s
  ushl v4.2s, v8.2s, v9.2s
  ushl v5.2s, v8.2s, v9.2s
  ushl v6.2s, v8.2s, v9.2s
  ushl v7.2s, v8.2s, v9.2s
  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)03071e3f51inst 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
8020420060156004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051103162220035800001002003920039200392003920039
8020420038155004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000351102162220035800001002003920039200392003920039
8020420038155004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038155004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038156004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
8020420038155004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001001051102162220035800001002003920039200392003920039
8020420038156006825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001002051102162220035800001002003920039200392003920039
8020420038155094025801001008000010080000500640000020019200382003899733999680100200800962001600002003820038118020110099100100800001001351102162220035800001002003920039200392003920039
80204200381550184025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381550023025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a0b18191e1f3a3f51inst 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)5f60696d6edispatch 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)9fa0a1a6a8a9acc2cfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000000324258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502011160111020035080000102003920039200392003920039
8002420038160000000039258001010800001080000506400001120019200382003899963100188001020800002016000020038200381180021109101080000100000000502011160131220035080000102003920039200392003920039
800242003815500000003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010000001650502013160111120035080000102003920039200392003920039
80024200381550000000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000010990502012160111220035080000102003920039200392003920039
8002420038155000000039258001010800001080000606400000120019200382008799963100188001020800002016000020038200381180021109101080000100000000502012160121320035080000102003920039200392003920039
8002420038155000000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000030502011160121320035080000102003920039200392003920039
8002420038155000000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000090502012160121320035080000102003920039200392003920039
8002420038155000000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000030502010160111320035080000102003920039200392003920039
8002420038156000000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000030502012160131120035080000102003920039200392003920039
8002420038155000000039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100001000502012160121220035080000102003920039200392003920039