Zen4 tuning part 1 - cost tables
Commit Message
Hi
this patch updates cost of znver4 mostly based on data measued by Agner Fog.
Compared to previous generations x87 became bit slower which is probably not
big deal (and we have minimal benchmarking coverage for it). One interesting
improvement is reducation of FMA cost. I also updated costs of AVX256
loads/stores based on latencies (not throughput which is twice of avx256).
Overall AVX512 vectorization seems to improve noticeably some of TSVC
benchmarks but since internally 512 vectors are split to 256 vectors it is
somewhat risky and does not win in SPEC scores (mostly by regressing benchmarks
with loop that have small trip count like x264 and exchange), so for now I am
going to set AVX256_OPTIMAL tune but I am still playing with it. We improved
since ZNVER1 on choosing vectorization size and also have vectorized
prologues/epilogues so it may be possible to make avx512 small win overall.
In general I would like to keep cost tables latency based unless we have
a good reason to not do so. There are some interesting diferences in
znver3 tables that I also patched and seems performance neutral. I will
send that separately.
Bootstrapped/regtested x86_64-linux, also benchmarked on SPEC2017 along
with AVX512 tuning. I plan to commit it tomorrow unless there are some
comments.
Honza
* x86-tune-costs.h (znver4_cost): Upate costs of FP and SSE moves,
division multiplication, gathers, L2 cache size, and more complex
FP instrutions.
Comments
On Tue, Dec 6, 2022 at 11:01 AM Jan Hubicka via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Hi
> this patch updates cost of znver4 mostly based on data measued by Agner Fog.
> Compared to previous generations x87 became bit slower which is probably not
> big deal (and we have minimal benchmarking coverage for it). One interesting
> improvement is reducation of FMA cost. I also updated costs of AVX256
> loads/stores based on latencies (not throughput which is twice of avx256).
> Overall AVX512 vectorization seems to improve noticeably some of TSVC
> benchmarks but since internally 512 vectors are split to 256 vectors it is
> somewhat risky and does not win in SPEC scores (mostly by regressing benchmarks
> with loop that have small trip count like x264 and exchange), so for now I am
> going to set AVX256_OPTIMAL tune but I am still playing with it. We improved
> since ZNVER1 on choosing vectorization size and also have vectorized
> prologues/epilogues so it may be possible to make avx512 small win overall.
>
> In general I would like to keep cost tables latency based unless we have
> a good reason to not do so. There are some interesting diferences in
> znver3 tables that I also patched and seems performance neutral. I will
> send that separately.
>
> Bootstrapped/regtested x86_64-linux, also benchmarked on SPEC2017 along
> with AVX512 tuning. I plan to commit it tomorrow unless there are some
> comments.
>
> Honza
>
> * x86-tune-costs.h (znver4_cost): Upate costs of FP and SSE moves,
> division multiplication, gathers, L2 cache size, and more complex
> FP instrutions.
> diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
> index f01b8ee9eef..3a6ce02f093 100644
> --- a/gcc/config/i386/x86-tune-costs.h
> +++ b/gcc/config/i386/x86-tune-costs.h
> @@ -1867,9 +1868,9 @@ struct processor_costs znver4_cost = {
> {8, 8, 8}, /* cost of storing integer
> registers. */
> 2, /* cost of reg,reg fld/fst. */
> - {6, 6, 16}, /* cost of loading fp registers
> + {14, 14, 17}, /* cost of loading fp registers
> in SFmode, DFmode and XFmode. */
> - {8, 8, 16}, /* cost of storing fp registers
> + {12, 12, 16}, /* cost of storing fp registers
> in SFmode, DFmode and XFmode. */
> 2, /* cost of moving MMX register. */
> {6, 6}, /* cost of loading MMX registers
> @@ -1878,13 +1879,13 @@ struct processor_costs znver4_cost = {
> in SImode and DImode. */
> 2, 2, 3, /* cost of moving XMM,YMM,ZMM
> register. */
> - {6, 6, 6, 6, 12}, /* cost of loading SSE registers
> + {6, 6, 10, 10, 12}, /* cost of loading SSE registers
> in 32,64,128,256 and 512-bit. */
> - {8, 8, 8, 8, 16}, /* cost of storing SSE registers
> + {8, 8, 8, 12, 12}, /* cost of storing SSE registers
> in 32,64,128,256 and 512-bit. */
> - 6, 6, /* SSE->integer and integer->SSE
> + 6, 8, /* SSE->integer and integer->SSE
> moves. */
> - 8, 8, /* mask->integer and integer->mask moves */
> + 8, 8, /* mask->integer and integer->mask moves */
> {6, 6, 6}, /* cost of loading mask register
> in QImode, HImode, SImode. */
> {8, 8, 8}, /* cost if storing mask register
> @@ -1894,6 +1895,7 @@ struct processor_costs znver4_cost = {
> },
>
> COSTS_N_INSNS (1), /* cost of an add instruction. */
> + /* TODO: Lea with 3 components has cost 2. */
> COSTS_N_INSNS (1), /* cost of a lea instruction. */
> COSTS_N_INSNS (1), /* variable shift costs. */
> COSTS_N_INSNS (1), /* constant shift costs. */
> @@ -1904,11 +1906,11 @@ struct processor_costs znver4_cost = {
> COSTS_N_INSNS (3)}, /* other. */
> 0, /* cost of multiply per each bit
> set. */
> - {COSTS_N_INSNS (9), /* cost of a divide/mod for QI. */
> - COSTS_N_INSNS (10), /* HI. */
> - COSTS_N_INSNS (12), /* SI. */
> - COSTS_N_INSNS (17), /* DI. */
> - COSTS_N_INSNS (17)}, /* other. */
> + {COSTS_N_INSNS (12), /* cost of a divide/mod for QI. */
> + COSTS_N_INSNS (13), /* HI. */
> + COSTS_N_INSNS (13), /* SI. */
> + COSTS_N_INSNS (18), /* DI. */
> + COSTS_N_INSNS (18)}, /* other. */
> COSTS_N_INSNS (1), /* cost of movsx. */
> COSTS_N_INSNS (1), /* cost of movzx. */
> 8, /* "large" insn. */
> @@ -1919,22 +1921,22 @@ struct processor_costs znver4_cost = {
> Relative to reg-reg move (2). */
> {8, 8, 8}, /* cost of storing integer
> registers. */
> - {6, 6, 6, 6, 12}, /* cost of loading SSE registers
> + {6, 6, 10, 10, 12}, /* cost of loading SSE registers
> in 32bit, 64bit, 128bit, 256bit and 512bit */
> - {8, 8, 8, 8, 16}, /* cost of storing SSE register
> + {8, 8, 8, 12, 12}, /* cost of storing SSE register
> in 32bit, 64bit, 128bit, 256bit and 512bit */
> - {6, 6, 6, 6, 12}, /* cost of unaligned loads. */
> - {8, 8, 8, 8, 16}, /* cost of unaligned stores. */
> - 2, 2, 3, /* cost of moving XMM,YMM,ZMM
> + {6, 6, 6, 6, 6}, /* cost of unaligned loads. */
> + {8, 8, 8, 8, 8}, /* cost of unaligned stores. */
> + 2, 2, 2, /* cost of moving XMM,YMM,ZMM
> register. */
> 6, /* cost of moving SSE register to integer. */
> - /* VGATHERDPD is 15 uops and throughput is 4, VGATHERDPS is 23 uops,
> - throughput 9. Approx 7 uops do not depend on vector size and every load
> - is 4 uops. */
> - 14, 8, /* Gather load static, per_elt. */
> - 14, 10, /* Gather store static, per_elt. */
> + /* VGATHERDPD is 17 uops and throughput is 4, VGATHERDPS is 24 uops,
> + throughput 5. Approx 7 uops do not depend on vector size and every load
> + is 5 uops. */
> + 14, 10, /* Gather load static, per_elt. */
> + 14, 20, /* Gather store static, per_elt. */
> 32, /* size of l1 cache. */
> - 512, /* size of l2 cache. */
> + 1024, /* size of l2 cache. */
> 64, /* size of prefetch block. */
> /* New AMD processors never drop prefetches; if they cannot be performed
> immediately, they are queued. We set number of simultaneous prefetches
> @@ -1943,26 +1945,26 @@ struct processor_costs znver4_cost = {
> time). */
> 100, /* number of parallel prefetches. */
> 3, /* Branch cost. */
> - COSTS_N_INSNS (5), /* cost of FADD and FSUB insns. */
> - COSTS_N_INSNS (5), /* cost of FMUL instruction. */
> + COSTS_N_INSNS (7), /* cost of FADD and FSUB insns. */
> + COSTS_N_INSNS (7), /* cost of FMUL instruction. */
> /* Latency of fdiv is 8-15. */
> COSTS_N_INSNS (15), /* cost of FDIV instruction. */
> COSTS_N_INSNS (1), /* cost of FABS instruction. */
> COSTS_N_INSNS (1), /* cost of FCHS instruction. */
> /* Latency of fsqrt is 4-10. */
the above comment looks like it needs updating as well
> - COSTS_N_INSNS (10), /* cost of FSQRT instruction. */
> + COSTS_N_INSNS (25), /* cost of FSQRT instruction. */
>
> COSTS_N_INSNS (1), /* cost of cheap SSE instruction. */
> COSTS_N_INSNS (3), /* cost of ADDSS/SD SUBSS/SD insns. */
> COSTS_N_INSNS (3), /* cost of MULSS instruction. */
> COSTS_N_INSNS (3), /* cost of MULSD instruction. */
> - COSTS_N_INSNS (5), /* cost of FMA SS instruction. */
> - COSTS_N_INSNS (5), /* cost of FMA SD instruction. */
> - COSTS_N_INSNS (10), /* cost of DIVSS instruction. */
> + COSTS_N_INSNS (4), /* cost of FMA SS instruction. */
> + COSTS_N_INSNS (4), /* cost of FMA SD instruction. */
> + COSTS_N_INSNS (13), /* cost of DIVSS instruction. */
> /* 9-13. */
> COSTS_N_INSNS (13), /* cost of DIVSD instruction. */
> - COSTS_N_INSNS (10), /* cost of SQRTSS instruction. */
> - COSTS_N_INSNS (15), /* cost of SQRTSD instruction. */
> + COSTS_N_INSNS (15), /* cost of SQRTSS instruction. */
> + COSTS_N_INSNS (21), /* cost of SQRTSD instruction. */
> /* Zen can execute 4 integer operations per cycle. FP operations
> take 3 cycles and it can execute 2 integer additions and 2
> multiplications thus reassociation may make sense up to with of 6.
> > - COSTS_N_INSNS (5), /* cost of FADD and FSUB insns. */
> > - COSTS_N_INSNS (5), /* cost of FMUL instruction. */
> > + COSTS_N_INSNS (7), /* cost of FADD and FSUB insns. */
> > + COSTS_N_INSNS (7), /* cost of FMUL instruction. */
> > /* Latency of fdiv is 8-15. */
> > COSTS_N_INSNS (15), /* cost of FDIV instruction. */
> > COSTS_N_INSNS (1), /* cost of FABS instruction. */
> > COSTS_N_INSNS (1), /* cost of FCHS instruction. */
> > /* Latency of fsqrt is 4-10. */
>
> the above comment looks like it needs updating as well
You are right. I will go through the comments for all zen revisions
incrementally. Many of them are outdated are still referes to znver1.
Honza
[AMD Official Use Only - General]
Hi Honza,
Thank you for posting the tuning patch.
> -----Original Message-----
> From: Jan Hubicka <hubicka@ucw.cz>
> Sent: Tuesday, December 6, 2022 3:31 PM
> To: gcc-patches@gcc.gnu.org; mjambor@suse.cz; Alexander Monakov
> <amonakov@ispras.ru>; Kumar, Venkataramanan
> <Venkataramanan.Kumar@amd.com>; Joshi, Tejas Sanjay
> <TejasSanjay.Joshi@amd.com>
> Subject: Zen4 tuning part 1 - cost tables
>
> Caution: This message originated from an External Source. Use proper
> caution when opening attachments, clicking links, or responding.
>
>
> Hi
> this patch updates cost of znver4 mostly based on data measued by Agner
> Fog.
> Compared to previous generations x87 became bit slower which is probably
> not big deal (and we have minimal benchmarking coverage for it). One
> interesting improvement is reducation of FMA cost. I also updated costs of
> AVX256 loads/stores based on latencies (not throughput which is twice of
> avx256).
> Overall AVX512 vectorization seems to improve noticeably some of TSVC
> benchmarks but since internally 512 vectors are split to 256 vectors it is
> somewhat risky and does not win in SPEC scores (mostly by regressing
> benchmarks with loop that have small trip count like x264 and exchange), so
> for now I am going to set AVX256_OPTIMAL tune but I am still playing with it.
> We improved since ZNVER1 on choosing vectorization size and also have
> vectorized prologues/epilogues so it may be possible to make avx512 small
> win overall.
I also noted improvements to TSVC benchmarks when we enable AVX512 vectorization. I think we should allow full AVX512 bit vectorization for znver4. Even if the 512 vectors are broken into two 256 vectors we can pipeline the higher half immediately in the next cycle. Also we have less instructions to decode with avx512 instructions. Overall AVX512 operations should be better.
>
> In general I would like to keep cost tables latency based unless we have a
> good reason to not do so. There are some interesting diferences in
> znver3 tables that I also patched and seems performance neutral. I will send
> that separately.
>
> Bootstrapped/regtested x86_64-linux, also benchmarked on SPEC2017 along
> with AVX512 tuning. I plan to commit it tomorrow unless there are some
> comments.
>
> Honza
>
> * x86-tune-costs.h (znver4_cost): Upate costs of FP and SSE moves,
> division multiplication, gathers, L2 cache size, and more complex
> FP instrutions.
> diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-
> costs.h
> index f01b8ee9eef..3a6ce02f093 100644
> --- a/gcc/config/i386/x86-tune-costs.h
> +++ b/gcc/config/i386/x86-tune-costs.h
> @@ -1867,9 +1868,9 @@ struct processor_costs znver4_cost = {
> {8, 8, 8}, /* cost of storing integer
> registers. */
> 2, /* cost of reg,reg fld/fst. */
> - {6, 6, 16}, /* cost of loading fp registers
> + {14, 14, 17}, /* cost of loading fp registers
> in SFmode, DFmode and XFmode. */
> - {8, 8, 16}, /* cost of storing fp registers
> + {12, 12, 16}, /* cost of storing fp registers
> in SFmode, DFmode and XFmode. */
> 2, /* cost of moving MMX register. */
> {6, 6}, /* cost of loading MMX registers
> @@ -1878,13 +1879,13 @@ struct processor_costs znver4_cost = {
> in SImode and DImode. */
> 2, 2, 3, /* cost of moving XMM,YMM,ZMM
> register. */
> - {6, 6, 6, 6, 12}, /* cost of loading SSE registers
> + {6, 6, 10, 10, 12}, /* cost of loading SSE registers
> in 32,64,128,256 and 512-bit. */
> - {8, 8, 8, 8, 16}, /* cost of storing SSE registers
> + {8, 8, 8, 12, 12}, /* cost of storing SSE registers
> in 32,64,128,256 and 512-bit. */
> - 6, 6, /* SSE->integer and integer->SSE
> + 6, 8, /* SSE->integer and integer->SSE
> moves. */
> - 8, 8, /* mask->integer and integer->mask moves */
> + 8, 8, /* mask->integer and integer->mask moves */
> {6, 6, 6}, /* cost of loading mask register
> in QImode, HImode, SImode. */
> {8, 8, 8}, /* cost if storing mask register
> @@ -1894,6 +1895,7 @@ struct processor_costs znver4_cost = {
> },
>
> COSTS_N_INSNS (1), /* cost of an add instruction. */
> + /* TODO: Lea with 3 components has cost 2. */
> COSTS_N_INSNS (1), /* cost of a lea instruction. */
> COSTS_N_INSNS (1), /* variable shift costs. */
> COSTS_N_INSNS (1), /* constant shift costs. */
> @@ -1904,11 +1906,11 @@ struct processor_costs znver4_cost = {
> COSTS_N_INSNS (3)}, /* other. */
> 0, /* cost of multiply per each bit
> set. */
> - {COSTS_N_INSNS (9), /* cost of a divide/mod for QI. */
> - COSTS_N_INSNS (10), /* HI. */
> - COSTS_N_INSNS (12), /* SI. */
> - COSTS_N_INSNS (17), /* DI. */
> - COSTS_N_INSNS (17)}, /* other. */
> + {COSTS_N_INSNS (12), /* cost of a divide/mod for QI. */
> + COSTS_N_INSNS (13), /* HI. */
> + COSTS_N_INSNS (13), /* SI. */
> + COSTS_N_INSNS (18), /* DI. */
> + COSTS_N_INSNS (18)}, /* other. */
> COSTS_N_INSNS (1), /* cost of movsx. */
> COSTS_N_INSNS (1), /* cost of movzx. */
> 8, /* "large" insn. */
> @@ -1919,22 +1921,22 @@ struct processor_costs znver4_cost = {
> Relative to reg-reg move (2). */
> {8, 8, 8}, /* cost of storing integer
> registers. */
> - {6, 6, 6, 6, 12}, /* cost of loading SSE registers
> + {6, 6, 10, 10, 12}, /* cost of loading SSE registers
> in 32bit, 64bit, 128bit, 256bit and 512bit */
> - {8, 8, 8, 8, 16}, /* cost of storing SSE register
> + {8, 8, 8, 12, 12}, /* cost of storing SSE register
> in 32bit, 64bit, 128bit, 256bit and 512bit */
> - {6, 6, 6, 6, 12}, /* cost of unaligned loads. */
> - {8, 8, 8, 8, 16}, /* cost of unaligned stores. */
> - 2, 2, 3, /* cost of moving XMM,YMM,ZMM
> + {6, 6, 6, 6, 6}, /* cost of unaligned loads. */
> + {8, 8, 8, 8, 8}, /* cost of unaligned stores. */
> + 2, 2, 2, /* cost of moving XMM,YMM,ZMM
> register. */
> 6, /* cost of moving SSE register to integer. */
> - /* VGATHERDPD is 15 uops and throughput is 4, VGATHERDPS is 23 uops,
> - throughput 9. Approx 7 uops do not depend on vector size and every
> load
> - is 4 uops. */
> - 14, 8, /* Gather load static, per_elt. */
> - 14, 10, /* Gather store static, per_elt. */
> + /* VGATHERDPD is 17 uops and throughput is 4, VGATHERDPS is 24 uops,
> + throughput 5. Approx 7 uops do not depend on vector size and every
> load
> + is 5 uops. */
> + 14, 10, /* Gather load static, per_elt. */
> + 14, 20, /* Gather store static, per_elt. */
> 32, /* size of l1 cache. */
> - 512, /* size of l2 cache. */
> + 1024, /* size of l2 cache. */
> 64, /* size of prefetch block. */
> /* New AMD processors never drop prefetches; if they cannot be
> performed
> immediately, they are queued. We set number of simultaneous
> prefetches @@ -1943,26 +1945,26 @@ struct processor_costs znver4_cost =
> {
> time). */
> 100, /* number of parallel prefetches. */
> 3, /* Branch cost. */
> - COSTS_N_INSNS (5), /* cost of FADD and FSUB insns. */
> - COSTS_N_INSNS (5), /* cost of FMUL instruction. */
> + COSTS_N_INSNS (7), /* cost of FADD and FSUB insns. */
> + COSTS_N_INSNS (7), /* cost of FMUL instruction. */
> /* Latency of fdiv is 8-15. */
> COSTS_N_INSNS (15), /* cost of FDIV instruction. */
> COSTS_N_INSNS (1), /* cost of FABS instruction. */
> COSTS_N_INSNS (1), /* cost of FCHS instruction. */
> /* Latency of fsqrt is 4-10. */
> - COSTS_N_INSNS (10), /* cost of FSQRT instruction. */
> + COSTS_N_INSNS (25), /* cost of FSQRT instruction. */
>
> COSTS_N_INSNS (1), /* cost of cheap SSE instruction. */
> COSTS_N_INSNS (3), /* cost of ADDSS/SD SUBSS/SD insns. */
> COSTS_N_INSNS (3), /* cost of MULSS instruction. */
> COSTS_N_INSNS (3), /* cost of MULSD instruction. */
> - COSTS_N_INSNS (5), /* cost of FMA SS instruction. */
> - COSTS_N_INSNS (5), /* cost of FMA SD instruction. */
> - COSTS_N_INSNS (10), /* cost of DIVSS instruction. */
> + COSTS_N_INSNS (4), /* cost of FMA SS instruction. */
> + COSTS_N_INSNS (4), /* cost of FMA SD instruction. */
> + COSTS_N_INSNS (13), /* cost of DIVSS instruction. */
> /* 9-13. */
> COSTS_N_INSNS (13), /* cost of DIVSD instruction. */
> - COSTS_N_INSNS (10), /* cost of SQRTSS instruction. */
> - COSTS_N_INSNS (15), /* cost of SQRTSD instruction. */
> + COSTS_N_INSNS (15), /* cost of SQRTSS instruction. */
> + COSTS_N_INSNS (21), /* cost of SQRTSD instruction. */
> /* Zen can execute 4 integer operations per cycle. FP operations
> take 3 cycles and it can execute 2 integer additions and 2
> multiplications thus reassociation may make sense up to with of 6.
The cost changes looks fine.
Regards,
Venkat.
@@ -1867,9 +1868,9 @@ struct processor_costs znver4_cost = {
{8, 8, 8}, /* cost of storing integer
registers. */
2, /* cost of reg,reg fld/fst. */
- {6, 6, 16}, /* cost of loading fp registers
+ {14, 14, 17}, /* cost of loading fp registers
in SFmode, DFmode and XFmode. */
- {8, 8, 16}, /* cost of storing fp registers
+ {12, 12, 16}, /* cost of storing fp registers
in SFmode, DFmode and XFmode. */
2, /* cost of moving MMX register. */
{6, 6}, /* cost of loading MMX registers
@@ -1878,13 +1879,13 @@ struct processor_costs znver4_cost = {
in SImode and DImode. */
2, 2, 3, /* cost of moving XMM,YMM,ZMM
register. */
- {6, 6, 6, 6, 12}, /* cost of loading SSE registers
+ {6, 6, 10, 10, 12}, /* cost of loading SSE registers
in 32,64,128,256 and 512-bit. */
- {8, 8, 8, 8, 16}, /* cost of storing SSE registers
+ {8, 8, 8, 12, 12}, /* cost of storing SSE registers
in 32,64,128,256 and 512-bit. */
- 6, 6, /* SSE->integer and integer->SSE
+ 6, 8, /* SSE->integer and integer->SSE
moves. */
- 8, 8, /* mask->integer and integer->mask moves */
+ 8, 8, /* mask->integer and integer->mask moves */
{6, 6, 6}, /* cost of loading mask register
in QImode, HImode, SImode. */
{8, 8, 8}, /* cost if storing mask register
@@ -1894,6 +1895,7 @@ struct processor_costs znver4_cost = {
},
COSTS_N_INSNS (1), /* cost of an add instruction. */
+ /* TODO: Lea with 3 components has cost 2. */
COSTS_N_INSNS (1), /* cost of a lea instruction. */
COSTS_N_INSNS (1), /* variable shift costs. */
COSTS_N_INSNS (1), /* constant shift costs. */
@@ -1904,11 +1906,11 @@ struct processor_costs znver4_cost = {
COSTS_N_INSNS (3)}, /* other. */
0, /* cost of multiply per each bit
set. */
- {COSTS_N_INSNS (9), /* cost of a divide/mod for QI. */
- COSTS_N_INSNS (10), /* HI. */
- COSTS_N_INSNS (12), /* SI. */
- COSTS_N_INSNS (17), /* DI. */
- COSTS_N_INSNS (17)}, /* other. */
+ {COSTS_N_INSNS (12), /* cost of a divide/mod for QI. */
+ COSTS_N_INSNS (13), /* HI. */
+ COSTS_N_INSNS (13), /* SI. */
+ COSTS_N_INSNS (18), /* DI. */
+ COSTS_N_INSNS (18)}, /* other. */
COSTS_N_INSNS (1), /* cost of movsx. */
COSTS_N_INSNS (1), /* cost of movzx. */
8, /* "large" insn. */
@@ -1919,22 +1921,22 @@ struct processor_costs znver4_cost = {
Relative to reg-reg move (2). */
{8, 8, 8}, /* cost of storing integer
registers. */
- {6, 6, 6, 6, 12}, /* cost of loading SSE registers
+ {6, 6, 10, 10, 12}, /* cost of loading SSE registers
in 32bit, 64bit, 128bit, 256bit and 512bit */
- {8, 8, 8, 8, 16}, /* cost of storing SSE register
+ {8, 8, 8, 12, 12}, /* cost of storing SSE register
in 32bit, 64bit, 128bit, 256bit and 512bit */
- {6, 6, 6, 6, 12}, /* cost of unaligned loads. */
- {8, 8, 8, 8, 16}, /* cost of unaligned stores. */
- 2, 2, 3, /* cost of moving XMM,YMM,ZMM
+ {6, 6, 6, 6, 6}, /* cost of unaligned loads. */
+ {8, 8, 8, 8, 8}, /* cost of unaligned stores. */
+ 2, 2, 2, /* cost of moving XMM,YMM,ZMM
register. */
6, /* cost of moving SSE register to integer. */
- /* VGATHERDPD is 15 uops and throughput is 4, VGATHERDPS is 23 uops,
- throughput 9. Approx 7 uops do not depend on vector size and every load
- is 4 uops. */
- 14, 8, /* Gather load static, per_elt. */
- 14, 10, /* Gather store static, per_elt. */
+ /* VGATHERDPD is 17 uops and throughput is 4, VGATHERDPS is 24 uops,
+ throughput 5. Approx 7 uops do not depend on vector size and every load
+ is 5 uops. */
+ 14, 10, /* Gather load static, per_elt. */
+ 14, 20, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
- 512, /* size of l2 cache. */
+ 1024, /* size of l2 cache. */
64, /* size of prefetch block. */
/* New AMD processors never drop prefetches; if they cannot be performed
immediately, they are queued. We set number of simultaneous prefetches
@@ -1943,26 +1945,26 @@ struct processor_costs znver4_cost = {
time). */
100, /* number of parallel prefetches. */
3, /* Branch cost. */
- COSTS_N_INSNS (5), /* cost of FADD and FSUB insns. */
- COSTS_N_INSNS (5), /* cost of FMUL instruction. */
+ COSTS_N_INSNS (7), /* cost of FADD and FSUB insns. */
+ COSTS_N_INSNS (7), /* cost of FMUL instruction. */
/* Latency of fdiv is 8-15. */
COSTS_N_INSNS (15), /* cost of FDIV instruction. */
COSTS_N_INSNS (1), /* cost of FABS instruction. */
COSTS_N_INSNS (1), /* cost of FCHS instruction. */
/* Latency of fsqrt is 4-10. */
- COSTS_N_INSNS (10), /* cost of FSQRT instruction. */
+ COSTS_N_INSNS (25), /* cost of FSQRT instruction. */
COSTS_N_INSNS (1), /* cost of cheap SSE instruction. */
COSTS_N_INSNS (3), /* cost of ADDSS/SD SUBSS/SD insns. */
COSTS_N_INSNS (3), /* cost of MULSS instruction. */
COSTS_N_INSNS (3), /* cost of MULSD instruction. */
- COSTS_N_INSNS (5), /* cost of FMA SS instruction. */
- COSTS_N_INSNS (5), /* cost of FMA SD instruction. */
- COSTS_N_INSNS (10), /* cost of DIVSS instruction. */
+ COSTS_N_INSNS (4), /* cost of FMA SS instruction. */
+ COSTS_N_INSNS (4), /* cost of FMA SD instruction. */
+ COSTS_N_INSNS (13), /* cost of DIVSS instruction. */
/* 9-13. */
COSTS_N_INSNS (13), /* cost of DIVSD instruction. */
- COSTS_N_INSNS (10), /* cost of SQRTSS instruction. */
- COSTS_N_INSNS (15), /* cost of SQRTSD instruction. */
+ COSTS_N_INSNS (15), /* cost of SQRTSS instruction. */
+ COSTS_N_INSNS (21), /* cost of SQRTSD instruction. */
/* Zen can execute 4 integer operations per cycle. FP operations
take 3 cycles and it can execute 2 integer additions and 2
multiplications thus reassociation may make sense up to with of 6.