Apple M1 Microarchitecture Research by Dougall Johnson

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

USUBW2 (vector, 2D)

Test 1: uops

Code:

  usubw2 v0.2d, v0.2d, v1.4s
  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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000373116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037160108416872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100002073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  usubw2 v0.2d, v0.2d, v1.4s
  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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715608219687251010010010000100100005002847680020018200372003718422318745101002001000020420330200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715606119687251010010010000100100005002847680020018200372003718425318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
102042003715506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000028119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006404163419785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403165419785010000102003820038200382003820038
100242003715000000008219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006404163419785010000102003820038200382003820038
10024200371500000000143619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006404164319785010000102003820038200382003820038
1002420037150000000035519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000008567564319785010000102008620038200382008620038
1002420131163014328226402301196874310010101001210100006528591510202702027620416184661918936110792011487202261420310202761110021109101010000100200394047085244419859010000102013220085200382003820038
1002420037155008800010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006404163419785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403164419785010000102003820038200382003820038
1002420037150000000012419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101000006404163419785010000102003820038200382003820038
1002420037150000000012619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006404164419785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  usubw2 v0.2d, v1.2d, v0.4s
  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)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)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)9fa6a8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371560363461968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102161119791100001002003820038200382003820038
10204200371550219611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037155018611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550231611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550537611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037155024611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100010007101161119791100001002003820038200382003820038
10204200371550153611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037161005361968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037155015611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006405163319851010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018020037200371846331876710010201000020200002003720037111002110910101000010006403163319785010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006403163319785010000102003820038200382003820038
10024200371550010319687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010020906403163319785010000102003820038200382003820038
10024200371550072619687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006403163319785010000102003820038200382003820038
1002420037155006119687251002210100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006403163319785010000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010106403173319785010000102003820038200382003820038
10024200371551208219687251001010100001010000502847680020018020037200371844431876710010201000020200002008420037111002110910101000010006403163319785010000102003820038200382003820038
10024200371552106119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006403163319785010000102003820038200382003820038
1002420037156606119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006403163319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  usubw2 v0.2d, v8.2d, v9.4s
  usubw2 v1.2d, v8.2d, v9.4s
  usubw2 v2.2d, v8.2d, v9.4s
  usubw2 v3.2d, v8.2d, v9.4s
  usubw2 v4.2d, v8.2d, v9.4s
  usubw2 v5.2d, v8.2d, v9.4s
  usubw2 v6.2d, v8.2d, v9.4s
  usubw2 v7.2d, v8.2d, v9.4s
  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)03080b18191e1f3f51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815500003906825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511021611200350800001002003920039200392003920039
802042003815500001504025801001008000012080097500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381560000304025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038161000029404025801001008000010080102500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815500001204025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381560000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381550000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155594090258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001001050203161120035080000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050202161120035080000102003920039200392003920039
800242003815615081258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
8002420038155405039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
80024200381562460392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000502014861120035080000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050202162220035080000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035180000102003920039200392003920039
80024200381550039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050201164420035080000102003920039200392003920039