Apple M1 Microarchitecture Research by Dougall Johnson

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

SRHADD (vector, 8H)

Test 1: uops

Code:

  srhadd v0.8h, v0.8h, v1.8h
  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)0308181e1f3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203716000061168725100010001000264680201820372037157231895100010002000203720371110011000001573216221787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100001073216221787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100090373216231787100020382038203820382038
1004203715000886116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715001206116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
100420371500306116872510001000100026468020182037203715723189510001000200020372037111001100003073216221787100020382038203820382038
100420371500006116872510001000100026468020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  srhadd v0.8h, v0.8h, v1.8h
  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)033f4e51inst 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)9fa8c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200183200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150726196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006403162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820086
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150007261968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  srhadd v0.8h, v1.8h, v0.8h
  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)030918191e3f4e51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500003061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002008520038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

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)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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003716127912771968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715005361968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371501831451968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820086200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001010640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001001640216221978510000102003820038200382003820038
10024200371550611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  srhadd v0.8h, v8.8h, v9.8h
  srhadd v1.8h, v8.8h, v9.8h
  srhadd v2.8h, v8.8h, v9.8h
  srhadd v3.8h, v8.8h, v9.8h
  srhadd v4.8h, v8.8h, v9.8h
  srhadd v5.8h, v8.8h, v9.8h
  srhadd v6.8h, v8.8h, v9.8h
  srhadd v7.8h, v8.8h, v9.8h
  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)031e3a3f51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006615000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003841802011009910010080000100000005110316112003500800001002003920039200952013820039
8020420038155840402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005110116112003500800001002003920039200392003920039
802042003815000452580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005110116112003500800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005110116112003500800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005110116112003500800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100001005110116112003500800001002003920039200392003920039
8020420038150150402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005110116112003500800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005110116112003500800001002003920039200392003920039
80204200381554508225801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000002405110116112003500800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100200005110116112003500800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502091607520035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502071607720035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502071607720035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920087200389996310018800102080000201600002003820038118002110910108000010000000000502071605720035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502051607720035080000102003920039200392003920039
80024200381500000000083258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502051607720035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000010000502071605720035080000102003920039200392003920039
80024200381500000060039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502051607520035080000102003920039200392003920039
80024200381500010000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502071605720035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000000502051605720035080000102003920039200392003920039