Apple M1 Microarchitecture Research by Dougall Johnson

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

CMTST (register, 2S)

Test 1: uops

Code:

  cmtst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715017016872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715010316872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmtst 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)0308181e3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100069007102161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000117007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000126119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100099207102251119791100001002008520038200382003820038
102042003715000126119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100096007101161119791100001002003820038200382003820038
10204200371500006341968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100099007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100081007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100093007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150007261968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221982310000102003820038200382003820038
1002420037150021611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000640216221978510000102003820133203242032320366

Test 3: Latency 1->3

Code:

  cmtst 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)0318191e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500096119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150002461196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000710348221996931100001002003820038200382003820275
10204202301520006119687251010011410060100100005002847680020018200372003718422318745101002021000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500038219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100371011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100071011611198620100001002003820038200382003820038

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)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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150025119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251002310100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150020819687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150078919687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150014519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001012100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmtst v0.2s, v8.2s, v9.2s
  cmtst v1.2s, v8.2s, v9.2s
  cmtst v2.2s, v8.2s, v9.2s
  cmtst v3.2s, v8.2s, v9.2s
  cmtst v4.2s, v8.2s, v9.2s
  cmtst v5.2s, v8.2s, v9.2s
  cmtst v6.2s, v8.2s, v9.2s
  cmtst 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)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)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
802042004715004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003815704025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150124025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101271120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004052801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051261161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308091e3f51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150020392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050206164220035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050204162420035080000102003920039200392003920039
800242003815000333392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050202162420035080000102003920039200392003920039
8002420038156000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050204164220035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050202162420035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050204164220035080000102003920039200392003920039
80024200381500001342580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050204164220035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050202162420035080000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050204164220035080000102003920039200392003920039
80024200381500021392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000050202162420035080000102003920039200392003920039