x86: Tune Skylake, Cannonlake and Icelake as Haswell

r259399, which added PROCESSOR_SKYLAKE, disabled many x86 optimizations
which are enabled by PROCESSOR_HASWELL.  As the result, -mtune=skylake
generates slower codes on Skylake than before.  The same also applies
to Cannonlake and Icelak tuning.

This patch changes -mtune={skylake|cannonlake|icelake} to tune like
-mtune=haswell for until their tuning is properly adjusted. It also
enables -mprefer-vector-width=256 for -mtune=haswell, which has no
impact on codegen when AVX512 isn't enabled.

Performance impacts on SPEC CPU 2017 rate with 1 copy using

-march=native -mfpmath=sse -O2 -m64

are

1. On Broadwell server:

500.perlbench_r		-0.56%
502.gcc_r		-0.18%
505.mcf_r		0.24%
520.omnetpp_r		0.00%
523.xalancbmk_r		-0.32%
525.x264_r		-0.17%
531.deepsjeng_r		0.00%
541.leela_r		0.00%
548.exchange2_r		0.12%
557.xz_r		0.00%
Geomean			0.00%

503.bwaves_r		0.00%
507.cactuBSSN_r		0.21%
508.namd_r		0.00%
510.parest_r		0.19%
511.povray_r		-0.48%
519.lbm_r		0.00%
521.wrf_r		0.28%
526.blender_r		0.19%
527.cam4_r		0.39%
538.imagick_r		0.00%
544.nab_r		-0.36%
549.fotonik3d_r		0.51%
554.roms_r		0.00%
Geomean			0.17%

On Skylake client:

500.perlbench_r		0.96%
502.gcc_r		0.13%
505.mcf_r		-1.03%
520.omnetpp_r		-1.11%
523.xalancbmk_r		1.02%
525.x264_r		0.50%
531.deepsjeng_r		2.97%
541.leela_r		0.50%
548.exchange2_r		-0.95%
557.xz_r		2.41%
Geomean			0.56%

503.bwaves_r		0.49%
507.cactuBSSN_r		3.17%
508.namd_r		4.05%
510.parest_r		0.15%
511.povray_r		0.80%
519.lbm_r		3.15%
521.wrf_r		10.56%
526.blender_r		2.97%
527.cam4_r		2.36%
538.imagick_r		46.40%
544.nab_r		2.04%
549.fotonik3d_r		0.00%
554.roms_r		1.27%
Geomean			5.49%

On Skylake server:

500.perlbench_r		0.71%
502.gcc_r		-0.51%
505.mcf_r		-1.06%
520.omnetpp_r		-0.33%
523.xalancbmk_r		-0.22%
525.x264_r		1.72%
531.deepsjeng_r		-0.26%
541.leela_r		0.57%
548.exchange2_r		-0.75%
557.xz_r		-1.28%
Geomean			-0.21%

503.bwaves_r		0.00%
507.cactuBSSN_r		2.66%
508.namd_r		3.67%
510.parest_r		1.25%
511.povray_r		2.26%
519.lbm_r		1.69%
521.wrf_r		11.03%
526.blender_r		3.39%
527.cam4_r		1.69%
538.imagick_r		64.59%
544.nab_r		-0.54%
549.fotonik3d_r		2.68%
554.roms_r		0.00%
Geomean			6.19%

This patch improves -march=native performance on Skylake up to 60% and
leaves -march=native performance unchanged on Haswell.

gcc/

2018-07-13  H.J. Lu  <hongjiu.lu@intel.com>
	    Sunil K Pandey  <sunil.k.pandey@intel.com>

	PR target/84413
	* config/i386/i386.c (m_CORE_AVX512): New.
	(m_CORE_AVX2): Likewise.
	(m_CORE_ALL): Add m_CORE_AVX2.
	* config/i386/x86-tune.def: Replace m_HASWELL with m_CORE_AVX2.
	Replace m_SKYLAKE_AVX512 with m_CORE_AVX512 on avx256_optimal
	and remove the rest of m_SKYLAKE_AVX512.

gcc/testsuite/

2018-07-13  H.J. Lu  <hongjiu.lu@intel.com>
	    Sunil K Pandey  <sunil.k.pandey@intel.com>

	PR target/84413
	* gcc.target/i386/pr84413-1.c: New test.
	* gcc.target/i386/pr84413-2.c: Likewise.
	* gcc.target/i386/pr84413-3.c: Likewise.

Co-Authored-By: Sunil K Pandey <sunil.k.pandey@intel.com>

From-SVN: r262649

ChangeLog

@@ -1,3 +1,14 @@
+2018-07-13  H.J. Lu  <hongjiu.lu@intel.com>
+	    Sunil K Pandey  <sunil.k.pandey@intel.com>
+
+	PR target/84413
+	* config/i386/i386.c (m_CORE_AVX512): New.
+	(m_CORE_AVX2): Likewise.
+	(m_CORE_ALL): Add m_CORE_AVX2.
+	* config/i386/x86-tune.def: Replace m_HASWELL with m_CORE_AVX2.
+	Replace m_SKYLAKE_AVX512 with m_CORE_AVX512 on avx256_optimal
+	and remove the rest of m_SKYLAKE_AVX512.
+
 2018-07-06  Sebastian Huber  <sebastian.huber@embedded-brains.de>
 
 	* config.sub: Sync with upstream version 2018-07-03.

gcc/config/i386/i386.c

@@ -138,7 +138,6 @@ const struct processor_costs *ix86_cost = NULL;
 #define m_NEHALEM (HOST_WIDE_INT_1U<<PROCESSOR_NEHALEM)
 #define m_SANDYBRIDGE (HOST_WIDE_INT_1U<<PROCESSOR_SANDYBRIDGE)
 #define m_HASWELL (HOST_WIDE_INT_1U<<PROCESSOR_HASWELL)
-#define m_CORE_ALL (m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_HASWELL)
 #define m_BONNELL (HOST_WIDE_INT_1U<<PROCESSOR_BONNELL)
 #define m_SILVERMONT (HOST_WIDE_INT_1U<<PROCESSOR_SILVERMONT)
 #define m_KNL (HOST_WIDE_INT_1U<<PROCESSOR_KNL)
@@ -148,6 +147,10 @@ const struct processor_costs *ix86_cost = NULL;
 #define m_CANNONLAKE (HOST_WIDE_INT_1U<<PROCESSOR_CANNONLAKE)
 #define m_ICELAKE_CLIENT (HOST_WIDE_INT_1U<<PROCESSOR_ICELAKE_CLIENT)
 #define m_ICELAKE_SERVER (HOST_WIDE_INT_1U<<PROCESSOR_ICELAKE_SERVER)
+#define m_CORE_AVX512 (m_SKYLAKE_AVX512 | m_CANNONLAKE \
+		       | m_ICELAKE_CLIENT | m_ICELAKE_SERVER)
+#define m_CORE_AVX2 (m_HASWELL | m_SKYLAKE | m_CORE_AVX512)
+#define m_CORE_ALL (m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_CORE_AVX2)
 #define m_GOLDMONT (HOST_WIDE_INT_1U<<PROCESSOR_GOLDMONT)
 #define m_GOLDMONT_PLUS (HOST_WIDE_INT_1U<<PROCESSOR_GOLDMONT_PLUS)
 #define m_TREMONT (HOST_WIDE_INT_1U<<PROCESSOR_TREMONT)

gcc/config/i386/x86-tune.def

@@ -49,9 +49,9 @@ DEF_TUNE (X86_TUNE_SCHEDULE, "schedule",
    over partial stores.  For example preffer MOVZBL or MOVQ to load 8bit
    value over movb.  */
 DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
-          m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_HASWELL
+          m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_CORE_AVX2
 	  | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL
-	  | m_KNL | m_KNM | m_AMD_MULTIPLE | m_SKYLAKE_AVX512 | m_TREMONT
+	  | m_KNL | m_KNM | m_AMD_MULTIPLE | m_TREMONT
 	  | m_GENERIC)
 
 /* X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY: This knob promotes all store
@@ -87,8 +87,8 @@ DEF_TUNE (X86_TUNE_PARTIAL_FLAG_REG_STALL, "partial_flag_reg_stall",
 DEF_TUNE (X86_TUNE_MOVX, "movx",
           m_PPRO | m_P4_NOCONA | m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE
 	  | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_KNL | m_KNM | m_INTEL
-	  | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE | m_SKYLAKE_AVX512
+	  | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE
-	  | m_HASWELL | m_TREMONT | m_GENERIC)
+	  | m_CORE_AVX2 | m_TREMONT | m_GENERIC)
 
 /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by
    full sized loads.  */
@@ -105,19 +105,19 @@ DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_32, "fuse_cmp_and_branch_32",
 /* X86_TUNE_FUSE_CMP_AND_BRANCH_64: Fuse compare with a subsequent
    conditional jump instruction for TARGET_64BIT.  */
 DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_64, "fuse_cmp_and_branch_64",
-	  m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_BDVER | m_ZNVER1 | m_GENERIC)
+	  m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_BDVER | m_ZNVER1 | m_GENERIC)
 
 /* X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS: Fuse compare with a
    subsequent conditional jump instruction when the condition jump
    check sign flag (SF) or overflow flag (OF).  */
 DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS, "fuse_cmp_and_branch_soflags",
-	  m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_BDVER | m_ZNVER1 | m_GENERIC)
+	  m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_BDVER | m_ZNVER1 | m_GENERIC)
 
 /* X86_TUNE_FUSE_ALU_AND_BRANCH: Fuse alu with a subsequent conditional
    jump instruction when the alu instruction produces the CCFLAG consumed by
    the conditional jump instruction. */
 DEF_TUNE (X86_TUNE_FUSE_ALU_AND_BRANCH, "fuse_alu_and_branch",
-          m_SANDYBRIDGE | m_HASWELL | m_GENERIC)
+          m_SANDYBRIDGE | m_CORE_AVX2 | m_GENERIC)
 
 
 /*****************************************************************************/
@@ -297,7 +297,7 @@ DEF_TUNE (X86_TUNE_USE_BT, "use_bt",
 /* X86_TUNE_AVOID_FALSE_DEP_FOR_BMI: Avoid false dependency
    for bit-manipulation instructions.  */
 DEF_TUNE (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI, "avoid_false_dep_for_bmi",
-	  m_SANDYBRIDGE | m_HASWELL | m_GENERIC)
+	  m_SANDYBRIDGE | m_CORE_AVX2 | m_GENERIC)
 
 /* X86_TUNE_ADJUST_UNROLL: This enables adjusting the unroll factor based
    on hardware capabilities. Bdver3 hardware has a loop buffer which makes
@@ -349,15 +349,15 @@ DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill",
 /* X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL: Use movups for misaligned loads instead
    of a sequence loading registers by parts.  */
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal",
-	  m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_SILVERMONT | m_KNL | m_KNM
+	  m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM
-	  | m_INTEL | m_SKYLAKE_AVX512 | m_GOLDMONT | m_GOLDMONT_PLUS
+	  | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS
 	  | m_TREMONT | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER1 | m_GENERIC)
 
 /* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores instead
    of a sequence loading registers by parts.  */
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal",
-	  m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_SILVERMONT | m_KNL | m_KNM
+	  m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM
-	  | m_INTEL | m_SKYLAKE_AVX512 | m_GOLDMONT | m_GOLDMONT_PLUS
+	  | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS
 	  | m_TREMONT | m_BDVER | m_ZNVER1 | m_GENERIC)
 
 /* Use packed single precision instructions where posisble.  I.e. movups instead
@@ -446,7 +446,7 @@ 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_SKYLAKE_AVX512)
+DEF_TUNE (X86_TUNE_AVX256_OPTIMAL, "avx256_optimal", m_CORE_AVX512)
 
 /*****************************************************************************/
 /* Historical relics: tuning flags that helps a specific old CPU designs     */

gcc/testsuite/ChangeLog

@@ -1,3 +1,11 @@
+2018-07-13  H.J. Lu  <hongjiu.lu@intel.com>
+	    Sunil K Pandey  <sunil.k.pandey@intel.com>
+
+	PR target/84413
+	* gcc.target/i386/pr84413-1.c: New test.
+	* gcc.target/i386/pr84413-2.c: Likewise.
+	* gcc.target/i386/pr84413-3.c: Likewise.
+
 2018-07-13  Bill Schmidt  <wschmidt@linux.ibm.com>
 	    Steve Munroe  <munroesj52@gmail.com>
 

gcc/testsuite/gcc.target/i386/pr84413-1.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=skylake-avx512" } */
+/* { dg-final { scan-assembler-not "%zmm\[0-9\]+" } } */
+/* { dg-final { scan-assembler "vmulpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]+" } } */
+
+#define N 1024
+
+double a[N], b[N], c[N];
+
+void
+avx512f_test (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    c[i] = a[i] * b[i];
+}

gcc/testsuite/gcc.target/i386/pr84413-2.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=cannonlake" } */
+/* { dg-final { scan-assembler-not "%zmm\[0-9\]+" } } */
+/* { dg-final { scan-assembler "vmulpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]+" } } */
+
+#define N 1024
+
+double a[N], b[N], c[N];
+
+void
+avx512f_test (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    c[i] = a[i] * b[i];
+}

gcc/testsuite/gcc.target/i386/pr84413-3.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=icelake-server" } */
+/* { dg-final { scan-assembler-not "%zmm\[0-9\]+" } } */
+/* { dg-final { scan-assembler "vmulpd\[ \\t\]+\[^\n\]*%ymm\[0-9\]+" } } */
+
+#define N 1024
+
+double a[N], b[N], c[N];
+
+void
+avx512f_test (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    c[i] = a[i] * b[i];
+}