Apple M1 Microarchitecture Research by Dougall Johnson

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

USUBL (vector, 2D)

Test 1: uops

Code:

  usubl v0.2d, 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)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
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
10042037160941687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371601031687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371612611687251000100010002646802018203720371572318951000100020002037203711100110001373116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038208520382038

Test 2: Latency 1->2

Code:

  usubl v0.2d, 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)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
102042003715500000025119676251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382007120038
102042003716100000040219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
10204200371560000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
10204200371550000009919687451010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000108710216221979100100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216221979100100001002003820038200382003820038
10204200371560000006119687251010010010000100100005502848963120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710216111979100100001002003820038200382003820038

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)60696d6edispatch stall (70)72scheduler 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
1002420037150155551968725100101010000101000050284768012001820037200841844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820179200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200841500611968745100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371506611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  usubl v0.2d, 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)03080a1e3f4e51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715502061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
10204200371560221611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100005107102162219791100001002003820038200382003820038
102042003716102061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715502061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715602061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715502061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715502061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715602061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715502079196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715502061196872510100100100001001000050028476802001820071200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b1e3a3f4e51inst 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
1002420037155101012272196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
1002420037156101012272196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000644101611101978510000102003820038200382003820038
10024200371551010926621968725100101110000101000050284768002001820037200371844431876710010201000020200002003720037211002110910101000010006441016581978510000102003820038200382003820038
100242003715610100268196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
1002420037155101002638196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
100242003715510100268196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
10024200371561010026819687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100064451610101978510000102003820038200382003820038
100242003715510110268196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038
10024200371551010027319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100064451610101978510000102003820038200382003820038
100242003715510109268196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000644101610101978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  usubl v0.2d, v8.2s, v9.2s
  usubl v1.2d, v8.2s, v9.2s
  usubl v2.2d, v8.2s, v9.2s
  usubl v3.2d, v8.2s, v9.2s
  usubl v4.2d, v8.2s, v9.2s
  usubl v5.2d, v8.2s, v9.2s
  usubl v6.2d, v8.2s, v9.2s
  usubl v7.2d, 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)03081e3f51inst 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)9fa0a6a8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591560040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511021601120035800001002003920039200392003920039
80204200381550068258010010080000100800005006400000200193200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000020511011651120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000010511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920039200392003920039
80204200381550040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000000511011601120035800001002003920090200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6daddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050156003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005020111606220035080000102003920039200392003920039
800242003815500632580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010100502061602620035080000102003920039200392003920039
800242003815503392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010060502021602220035080000102003920039200392003920039
800242003815500812580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502021602220035080000102024220039200392003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502021602220035080000102003920039200392003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502021606620035080000102003920039200392003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502031603620035080000102003920039200392003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502061603220035080000102003920039200392003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502061603220035080000102003920088200872003920039
800242003815500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502061602620035080000102003920039200392003920039