Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDW (vector, 2D)

Test 1: uops

Code:

  uaddw v0.2d, v0.2d, 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)03091e1f3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150001771687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000841687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371509881031687251000100010002646800201820372037157231895100010002000203720371110011000373116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddw v0.2d, v0.2d, 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)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)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)9fa1a8a9acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715005761196872510100100100001001000050028476802001820037200371842961874010100200100082002001620037200371110201100991001001000010000000111718001600198470100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842961874010100200100082002001620037200371110201100991001001000010000000111718001600198020100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000710011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020134200371110201100991001001000010000000000710011611197914100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000710011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000710011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000710011611197910100001002003820038200382003820038
10204200371500361196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000710011611197910100001002003820038200382003820038
10204200371500961196872510100100100001001000050028476802001820037200371842231874510100200100002002067020037200371110201100991001001000010001090000710011611197910100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010001000000710011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa0a8acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010059000640216221978510000102003820038200382003820038
1002420037150038219687251001010100001010000502847680020018200852003718444071878610010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500156119676251001010100001010000502847680120018200372003718448031876710163201000020200002003720037211002110910101000010000000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
100242003715006061196872510010101000010100005028476801200182003720037184440171876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037150006119687251002310100001010000502847680120054200372008418444031876710010201000020200002003720037111002110910101000010211985000640216221978510000102003820038200382003820038
100242003715004686119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500246119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037150096119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000640216231978510000102003820038200382003820038
10024200371501614719687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uaddw v0.2d, v1.2d, 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)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)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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382008720038
102042003715022505331968725101001001000010010000500284768002001820084200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100280007102162219858100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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
10024200371490000900346196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184523187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000066196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162319785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uaddw v0.2d, v8.2d, v9.2s
  uaddw v1.2d, v8.2d, v9.2s
  uaddw v2.2d, v8.2d, v9.2s
  uaddw v3.2d, v8.2d, v9.2s
  uaddw v4.2d, v8.2d, v9.2s
  uaddw v5.2d, v8.2d, v9.2s
  uaddw v6.2d, v8.2d, v9.2s
  uaddw v7.2d, v8.2d, 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)030b18191e1f3f51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150000690402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511031611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000200192003820038997326999680100200800972001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420089151011132884025801001008000010080000500640000200192003820038997381004780100200800002001600002003820038118020110099100100800001004200511011611200350800001002003920039200392003920099

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150042392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038100203100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003814900392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815003392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020116112003580000102003920039200392003920039