Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (vector, 4H)

Test 1: uops

Code:

  fcmeq v0.4h, v0.4h, v1.4h
  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)03080b18191e1f3f4e51inst 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)a0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073216111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100002000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
1004203715000000103168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500006061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq v0.4h, v0.4h, v1.4h
  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)03081e1f3f4e51inst 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)9facbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007421161119791100001002003820038200382003820038
102042003715000886119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000044119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002406119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382008520038
10204200371500006119687251010010010000100100005002850246120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f203f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687791001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318793100102010000202000020037200371110021109101010000101006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
10024200371500000210319687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100406403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmeq v0.4h, v1.4h, v0.4h
  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)9fa8a9acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161219791100001002003820038200382003820038
1020420037158072719687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820216202301842231874510100200100002002000020037200371110201100991001001000010000129007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000183007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100002015027101161119791100001002003820038200382003820038
1020420037150053619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715008219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715508219687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010136402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150012419687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038
1002420037150052919687251001010100001010150502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715008419687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150036919687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmeq v0.4h, v8.4h, v9.4h
  fcmeq v1.4h, v8.4h, v9.4h
  fcmeq v2.4h, v8.4h, v9.4h
  fcmeq v3.4h, v8.4h, v9.4h
  fcmeq v4.4h, v8.4h, v9.4h
  fcmeq v5.4h, v8.4h, v9.4h
  fcmeq v6.4h, v8.4h, v9.4h
  fcmeq v7.4h, v8.4h, v9.4h
  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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058151040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010351102161120035800001002003920039200392003920039
8020420038150082258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
80204200381500124258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010351101161120035800001002003920039200392003920039
80204200381500189258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000351101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500211258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e3a3f51inst 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)5f696d6edispatch 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)9fa1a8a9acc2cfd5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000622580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502031650112003580000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650112003580000102003920039200392003920039
80024200381500000392580088108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650112003580000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011651212003580000102003920039200392003920039
80024200381500000812580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650222003580000102003920039200392003920039
80024200381490000812580010108000010800005064000012001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650112003580000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011652112003580000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650112003580000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650112003580000102003920039200392003920039
80024200381500000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000000502011650212003580000102003920039200392003920039