Zen4 tuning part 2

Adds tunes needed for zen4 microarchitecture.  I added two new knobs.
TARGET_AVX512_SPLIT_REGS which is used to specify that internally 512 vectors
are split to 256 vectors.  This affects vectorization costs and reassociation
width. It probably should also affect RTX costs however I doubt it is very useful
since RTL optimizers are usually not judging between 256 and 512 vectors.

I also added X86_TUNE_AVOID_256FMA_CHAINS. Since fma has improved in zen4 this
flag may not be a win except for very specific benchmarks. I am still doing some
more detailed testing here.

Oherwise I disabled gathers on zen4 for 2 parts nad 4 parts. We can open code them
and since the latencies has only increased since zen3 opencoding is better than
actual instrucction.  This shows at 4 tsvc benchmarks.

I ended up setting AVX256_OPTIMAL. This is a compromise.  There are some tsvc
benchmarks that increase noticeably (up to 250%) however there are also few
regressions.  Most of these can be solved by incrasing vec_perm cost in the
vectorizer.  However this does not cure about 14% regression on x264 that is
quite important.  Here we produce vectorized loops for avx512 that probably
would be faster if the loops in question had high enough iteration count.
We hit this problem with avx256 too: since the loop iterates few times, only
prologues/epilogues are used.  Adding another round of prologue/epilogue
code does not make it better.

Finally I enabled avx stores for constnat sized memcpy and memset.  I am not
sure why this is an opt-in feature.  I think for most hardware this is a win.

gcc/ChangeLog:

2022-12-22  Jan Hubicka  <hubicka@ucw.cz>

	* config/i386/i386-expand.cc (ix86_expand_set_or_cpymem): Add
	TARGET_AVX512_SPLIT_REGS
	* config/i386/i386-options.cc (ix86_option_override_internal):
	Honor x86_TONE_AVOID_256FMA_CHAINS.
	* config/i386/i386.cc (ix86_vec_cost): Honor TARGET_AVX512_SPLIT_REGS.
	(ix86_reassociation_width): Likewise.
	* config/i386/i386.h (TARGET_AVX512_SPLIT_REGS): New tune.
	* config/i386/x86-tune.def (X86_TUNE_USE_GATHER_2PARTS): Disable
	for znver4.
	(X86_TUNE_USE_GATHER_4PARTS): Likewise.
	(X86_TUNE_AVOID_256FMA_CHAINS): Set for znver4.
	(X86_TUNE_AVOID_512FMA_CHAINS): New utne; set for znver4.
	(X86_TUNE_AVX256_OPTIMAL): Add znver4.
	(X86_TUNE_AVX512_SPLIT_REGS): New tune.
	(X86_TUNE_AVX256_MOVE_BY_PIECES): Add znver1-3.
	(X86_TUNE_AVX256_STORE_BY_PIECES): Add znver1-3.
	(X86_TUNE_AVX512_MOVE_BY_PIECES): Add znver4.
	(X86_TUNE_AVX512_STORE_BY_PIECES): Add znver4.

(cherry picked from commit eef81eefcdc2a58111e50eb2162ea1f5becc8004)

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index faa63a48bcde1265a576018a9d330da8e40d2a1b..c967817726c5230e074a558ceec1072f2a376abb 100644 (file)
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -8461,6 +8461,8 @@ ix86_expand_set_or_cpymem (rtx dst, rtx src, rtx count_exp, rtx val_exp,
 
       if (TARGET_AVX256_SPLIT_REGS && GET_MODE_BITSIZE (move_mode) > 128)
        move_mode = TImode;
+      if (TARGET_AVX512_SPLIT_REGS && GET_MODE_BITSIZE (move_mode) > 256)
+       move_mode = OImode;
 
       /* Find the corresponding vector mode with the same size as MOVE_MODE.
         MOVE_MODE is an integer mode at the moment (SI, DI, TI, etc.).  */

diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 520da45097a3059751a348851abbdede6bbeb5a6..b9bce613f2588847cb91aca6160a5c35a64746c2 100644 (file)
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -2936,6 +2936,8 @@ ix86_option_override_internal (bool main_args_p,
     }
 
   if (ix86_tune_features [X86_TUNE_AVOID_256FMA_CHAINS])
+    SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 512);
+  else if (ix86_tune_features [X86_TUNE_AVOID_256FMA_CHAINS])
     SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 256);
   else if (ix86_tune_features [X86_TUNE_AVOID_128FMA_CHAINS])
     SET_OPTION_IF_UNSET (opts, opts_set, param_avoid_fma_max_bits, 128);

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 4ead65c921fbe5d948229ca0c7516e91c8171383..ad37f84fe06341ef52756a886cc51ba9347a2c53 100644 (file)
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -20218,10 +20218,13 @@ ix86_vec_cost (machine_mode mode, int cost)
 
   if (GET_MODE_BITSIZE (mode) == 128
       && TARGET_SSE_SPLIT_REGS)
-    return cost * 2;
-  if (GET_MODE_BITSIZE (mode) > 128
+    return cost * GET_MODE_BITSIZE (mode) / 64;
+  else if (GET_MODE_BITSIZE (mode) > 128
       && TARGET_AVX256_SPLIT_REGS)
     return cost * GET_MODE_BITSIZE (mode) / 128;
+  else if (GET_MODE_BITSIZE (mode) > 256
+      && TARGET_AVX512_SPLIT_REGS)
+    return cost * GET_MODE_BITSIZE (mode) / 256;
   return cost;
 }
 
@@ -22803,7 +22806,9 @@ ix86_reassociation_width (unsigned int op, machine_mode mode)
        return 1;
 
       /* Account for targets that splits wide vectors into multiple parts.  */
-      if (TARGET_AVX256_SPLIT_REGS && GET_MODE_BITSIZE (mode) > 128)
+      if (TARGET_AVX512_SPLIT_REGS && GET_MODE_BITSIZE (mode) > 256)
+       div = GET_MODE_BITSIZE (mode) / 256;
+      else if (TARGET_AVX256_SPLIT_REGS && GET_MODE_BITSIZE (mode) > 128)
        div = GET_MODE_BITSIZE (mode) / 128;
       else if (TARGET_SSE_SPLIT_REGS && GET_MODE_BITSIZE (mode) > 64)
        div = GET_MODE_BITSIZE (mode) / 64;

diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 009c5b5a7b9ccf506422c72315e07f2fd796d393..7a079072e19d27f9616501ca974e65740dc72662 100644 (file)
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -414,6 +414,8 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
        ix86_tune_features[X86_TUNE_SOFTWARE_PREFETCHING_BENEFICIAL]
 #define TARGET_AVX256_SPLIT_REGS \
        ix86_tune_features[X86_TUNE_AVX256_SPLIT_REGS]
+#define TARGET_AVX512_SPLIT_REGS \
+       ix86_tune_features[X86_TUNE_AVX512_SPLIT_REGS]
 #define TARGET_GENERAL_REGS_SSE_SPILL \
        ix86_tune_features[X86_TUNE_GENERAL_REGS_SSE_SPILL]
 #define TARGET_AVOID_MEM_OPND_FOR_CMOVE \

diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 1e1b206a71c6434380914fa27e43f79319217d9d..eb3ab8002642999ea2786cf1caf5aa3d88247909 100644 (file)
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -467,12 +467,12 @@ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
 /* X86_TUNE_USE_GATHER_2PARTS: Use gather instructions for vectors with 2
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts",
-         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_GENERIC))
+         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE | m_GENERIC))
 
 /* X86_TUNE_USE_GATHER_4PARTS: Use gather instructions for vectors with 4
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts",
-         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ALDERLAKE | m_GENERIC))
+         ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 |  m_ALDERLAKE | m_GENERIC))
 
 /* X86_TUNE_USE_GATHER: Use gather instructions for vectors with 8 or more
    elements.  */
@@ -485,9 +485,13 @@ DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER)
 
 /* X86_TUNE_AVOID_256FMA_CHAINS: Avoid creating loops with tight 256bit or
    smaller FMA chain.  */
-DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 | m_ZNVER3
+DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 | m_ZNVER3 | m_ZNVER4
          | m_ALDERLAKE | m_SAPPHIRERAPIDS)
 
+/* X86_TUNE_AVOID_512FMA_CHAINS: Avoid creating loops with tight 512bit or
+   smaller FMA chain.  */
+DEF_TUNE (X86_TUNE_AVOID_512FMA_CHAINS, "avoid_fma512_chains", m_ZNVER4)
+
 /* X86_TUNE_V2DF_REDUCTION_PREFER_PHADDPD: Prefer haddpd
    for v2df vector reduction.  */
 DEF_TUNE (X86_TUNE_V2DF_REDUCTION_PREFER_HADDPD,
@@ -518,27 +522,30 @@ DEF_TUNE (X86_TUNE_AVX128_OPTIMAL, "avx128_optimal", m_BDVER | m_BTVER2
 
 /* X86_TUNE_AVX256_OPTIMAL: Use 256-bit AVX instructions instead of 512-bit AVX
    instructions in the auto-vectorizer.  */
-DEF_TUNE (X86_TUNE_AVX256_OPTIMAL, "avx256_optimal", m_CORE_AVX512)
+DEF_TUNE (X86_TUNE_AVX256_OPTIMAL, "avx256_optimal", m_CORE_AVX512 | m_ZNVER4)
+
+/* X86_TUNE_AVX256_SPLIT_REGS: if true, AVX512 ops are split into two AVX256 ops.  */
+DEF_TUNE (X86_TUNE_AVX512_SPLIT_REGS, "avx512_split_regs", m_ZNVER4)
 
 /* X86_TUNE_AVX256_MOVE_BY_PIECES: Optimize move_by_pieces with 256-bit
    AVX instructions.  */
 DEF_TUNE (X86_TUNE_AVX256_MOVE_BY_PIECES, "avx256_move_by_pieces",
-         m_CORE_AVX512)
+         m_CORE_AVX512 | m_ZNVER1 | m_ZNVER2 | m_ZNVER3)
 
 /* X86_TUNE_AVX256_STORE_BY_PIECES: Optimize store_by_pieces with 256-bit
    AVX instructions.  */
 DEF_TUNE (X86_TUNE_AVX256_STORE_BY_PIECES, "avx256_store_by_pieces",
-         m_CORE_AVX512)
+         m_CORE_AVX512 | m_ZNVER1 | m_ZNVER2 | m_ZNVER3)
 
 /* X86_TUNE_AVX512_MOVE_BY_PIECES: Optimize move_by_pieces with 512-bit
    AVX instructions.  */
 DEF_TUNE (X86_TUNE_AVX512_MOVE_BY_PIECES, "avx512_move_by_pieces",
-         m_SAPPHIRERAPIDS)
+         m_SAPPHIRERAPIDS | m_ZNVER4)
 
 /* X86_TUNE_AVX512_STORE_BY_PIECES: Optimize store_by_pieces with 512-bit
    AVX instructions.  */
 DEF_TUNE (X86_TUNE_AVX512_STORE_BY_PIECES, "avx512_store_by_pieces",
-         m_SAPPHIRERAPIDS)
+         m_SAPPHIRERAPIDS | m_ZNVER4)
 
 /*****************************************************************************/
 /*****************************************************************************/