Apple M1 Microarchitecture Research by Dougall Johnson

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

FMIN (vector, 4S)

Test 1: uops

Code:

  fmin v0.4s, v0.4s, 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)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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100001873316331787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100017073316331787100020382038203820382038
1004203716246116872510001000100026468002018203720371572318951000100020002037203711100110000073216331787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100001573316331787100020382038203820382038
10042037161561168725100010001000264680120182037203715723189510001000200020372037111001100001273316331787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmin v0.4s, v0.4s, 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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150033419687251010010010000100100005002847680120018320037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150126119687251010010010000100100005002847680120018020037200371842231874510270200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010027101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150012419687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150010319687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715008219687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001001710640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010200640216231978510000102003820038200382003820038
10024200371500147196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216131978510000102003820038200382003820038
1002420037150961196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
10024200371500726196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmin v0.4s, v1.4s, 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)030708191e1f3f4e51inst 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
102042003715000000103196872510100100100001251000062628476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100011471021622197910100001002003820038200382003820038
102042003715000036061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071031622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000646196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021722197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000821968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006441968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006612162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000007941968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000007261968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006551968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmin v0.4s, v8.4s, v9.4s
  fmin v1.4s, v8.4s, v9.4s
  fmin v2.4s, v8.4s, v9.4s
  fmin v3.4s, v8.4s, v9.4s
  fmin v4.4s, v8.4s, v9.4s
  fmin v5.4s, v8.4s, v9.4s
  fmin v6.4s, v8.4s, v9.4s
  fmin v7.4s, v8.4s, 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)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
802042004915004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051123161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
8020420038150040925801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815006125801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039
802042003815006325801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051121161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)5f60696b6d6edispatch 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)9fa0a8accfd5d6daddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150015039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502051605320035080000102003920039200392003920039
800242003815000039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502021603620035080000102003920039200392003920039
80024200381500372039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502021603220035080000102003920039200392003920039
8002420038150018039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010010502031602320035080000102003920039200392003920039
800242003815000039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502051603620035080000102003920039200392003920039
800242003815000039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502031604520035080000102003920039200392003920039
800242003815000039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502031606520035080000102003920039200392003920039
800242003815000039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502031603320035080000102003920039200392003920039
800242003815003352392580010108000010800005064000000200190200382003899963100188001020800002016000020038200381180021109101080000100135020316023200351680000102003920039200392003920039
800242003815000039258001010800001080000506400000020019020038200389996310018800102080000201600002003820038118002110910108000010000502031603620035080000102003920039200392003920039