[AArch64][1/2] Implement TARGET_ESTIMATED_POLY_VALUE

The hook TARGET_ESTIMATED_POLY_VALUE allows a target to give an estimate for a poly_int run-time value.
It is used exclusively in tuning decisions, things like estimated loop iterations, probabilities etc.
It is not relied on for correctness.

If we know the SVE width implemented in hardware we can make more more
informed decisions in the implementation of TARGET_ESTIMATED_POLY_VALUE,
even when compiling for VLA vectorisation.

This patch adds an sve_width field to our tuning structs and sets it for
the current CPU tunings.

A new value is introduced to the aarch64_sve_vector_bits_enum enum that indicates
that SVE is not available: SVE_NOT_IMPLEMENTED. I set it to the same value as SVE_SCALABLE
so that parts of the aarch64 backend that follow the pattern:
if (vector_width == SVE_SCALABLE)
  do_vla_friendly_action ()
else
  assume_specific_width_for_correctness ()

continue to work without change, but the CPU tuning structs can use a more
appropriate moniker for indicating the absence of SVE.

This sets sve_width to SVE_NOT_IMPLEMENTED for all cores.
I aim to add an -moverride switch in the next patch that allows a power user to experiment
with different values of it for investigations.

	* config/aarch64/aarch64-opts.h (aarch64_sve_vector_bits_enum):
	Add SVE_NOT_IMPLEMENTED value.
	* config/aarch64/aarch64-protos.h (struct tune_params): Add sve_width
	field.
	* config/aarch64/aarch64.c (generic_tunings,cortexa35_tunings,
	cortexa53_tunings, cortexa57_tunings, cortexa72_tunings,
	cortexa73_tunings, exynosm1_tunings, thunderx_tunings,
	thunderx_tunings, tsv110_tunings, xgene1_tunings, qdf24xx_tunings,
	saphira_tunings, thunderx2t99_tunings, emag_tunings):
	Specify sve_width.
	(aarch64_estimated_poly_value): Define.
	(TARGET_ESTIMATED_POLY_VALUE): Define.

From-SVN: r266896

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 39765211a7ac5d81b1d6d6d59cc29884fbe978ba..3f83c29dc36b9c472876dfcddd8e6986a16c8b91 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,18 @@
+2018-12-07  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
+       * config/aarch64/aarch64-opts.h (aarch64_sve_vector_bits_enum):
+       Add SVE_NOT_IMPLEMENTED value.
+       * config/aarch64/aarch64-protos.h (struct tune_params): Add sve_width
+       field.
+       * config/aarch64/aarch64.c (generic_tunings,cortexa35_tunings,
+       cortexa53_tunings, cortexa57_tunings, cortexa72_tunings,
+       cortexa73_tunings, exynosm1_tunings, thunderx_tunings,
+       thunderx_tunings, tsv110_tunings, xgene1_tunings, qdf24xx_tunings,
+       saphira_tunings, thunderx2t99_tunings, emag_tunings):
+       Specify sve_width.
+       (aarch64_estimated_poly_value): Define.
+       (TARGET_ESTIMATED_POLY_VALUE): Define.
+
 2018-12-07  Paul A. Clarke  <pc@us.ibm.com>
 
        PR target/88408

diff --git a/gcc/config/aarch64/aarch64-opts.h b/gcc/config/aarch64/aarch64-opts.h
index 7a5c6d7664f47b220840d7fdd4e68c5fedbb3d6e..1ac056b66dad21c51b740af82e77270074e87962 100644 (file)
--- a/gcc/config/aarch64/aarch64-opts.h
+++ b/gcc/config/aarch64/aarch64-opts.h
@@ -84,6 +84,7 @@ enum aarch64_function_type {
 /* SVE vector register sizes.  */
 enum aarch64_sve_vector_bits_enum {
   SVE_SCALABLE,
+  SVE_NOT_IMPLEMENTED = SVE_SCALABLE,
   SVE_128 = 128,
   SVE_256 = 256,
   SVE_512 = 512,

diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 1fe1a50d52aeb3719cf30c4a2af41abb8dd7233d..4ed886bd20049df10906a660c85c2fd9686e24d7 100644 (file)
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -252,6 +252,10 @@ struct tune_params
   const struct cpu_vector_cost *vec_costs;
   const struct cpu_branch_cost *branch_costs;
   const struct cpu_approx_modes *approx_modes;
+  /* Width of the SVE registers or SVE_NOT_IMPLEMENTED if not applicable.
+     Only used for tuning decisions, does not disable VLA
+     vectorization.  */
+  enum aarch64_sve_vector_bits_enum sve_width;
   int memmov_cost;
   int issue_rate;
   unsigned int fusible_ops;

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 490a2038b8e07502f385aa9237d59d8c2b9b31dd..ba9b5ad4efedf87c4ec247683e0435f14a7ef146 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -681,6 +681,7 @@ static const struct tune_params generic_tunings =
   &generic_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   2, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC), /* fusible_ops  */
@@ -706,6 +707,7 @@ static const struct tune_params cortexa35_tunings =
   &generic_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   1, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -732,6 +734,7 @@ static const struct tune_params cortexa53_tunings =
   &generic_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   2, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -758,6 +761,7 @@ static const struct tune_params cortexa57_tunings =
   &cortexa57_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   3, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -784,6 +788,7 @@ static const struct tune_params cortexa72_tunings =
   &cortexa57_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   3, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -810,6 +815,7 @@ static const struct tune_params cortexa73_tunings =
   &cortexa57_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost.  */
   2, /* issue_rate.  */
   (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -838,6 +844,7 @@ static const struct tune_params exynosm1_tunings =
   &exynosm1_vector_cost,
   &generic_branch_cost,
   &exynosm1_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4,   /* memmov_cost  */
   3,   /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC), /* fusible_ops  */
@@ -863,6 +870,7 @@ static const struct tune_params thunderxt88_tunings =
   &thunderx_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   6, /* memmov_cost  */
   2, /* issue_rate  */
   AARCH64_FUSE_CMP_BRANCH, /* fusible_ops  */
@@ -888,6 +896,7 @@ static const struct tune_params thunderx_tunings =
   &thunderx_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   6, /* memmov_cost  */
   2, /* issue_rate  */
   AARCH64_FUSE_CMP_BRANCH, /* fusible_ops  */
@@ -914,6 +923,7 @@ static const struct tune_params tsv110_tunings =
   &tsv110_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4,    /* memmov_cost  */
   4,    /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_CMP_BRANCH
@@ -940,6 +950,7 @@ static const struct tune_params xgene1_tunings =
   &xgene1_vector_cost,
   &generic_branch_cost,
   &xgene1_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   6, /* memmov_cost  */
   4, /* issue_rate  */
   AARCH64_FUSE_NOTHING, /* fusible_ops  */
@@ -965,6 +976,7 @@ static const struct tune_params emag_tunings =
   &xgene1_vector_cost,
   &generic_branch_cost,
   &xgene1_approx_modes,
+  SVE_NOT_IMPLEMENTED,
   6, /* memmov_cost  */
   4, /* issue_rate  */
   AARCH64_FUSE_NOTHING, /* fusible_ops  */
@@ -990,6 +1002,7 @@ static const struct tune_params qdf24xx_tunings =
   &qdf24xx_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   4, /* issue_rate  */
   (AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -1018,6 +1031,7 @@ static const struct tune_params saphira_tunings =
   &generic_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost  */
   4, /* issue_rate  */
   (AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
@@ -1044,6 +1058,7 @@ static const struct tune_params thunderx2t99_tunings =
   &thunderx2t99_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
+  SVE_NOT_IMPLEMENTED, /* sve_width  */
   4, /* memmov_cost.  */
   4, /* issue_rate.  */
   (AARCH64_FUSE_CMP_BRANCH | AARCH64_FUSE_AES_AESMC
@@ -17869,6 +17884,25 @@ aarch64_speculation_safe_value (machine_mode mode,
   return result;
 }
 
+/* Implement TARGET_ESTIMATED_POLY_VALUE.
+   Look into the tuning structure for an estimate.
+   VAL.coeffs[1] is multiplied by the number of VQ chunks over the initial
+   Advanced SIMD 128 bits.  */
+
+static HOST_WIDE_INT
+aarch64_estimated_poly_value (poly_int64 val)
+{
+  enum aarch64_sve_vector_bits_enum width_source
+    = aarch64_tune_params.sve_width;
+
+  /* If we still don't have an estimate, use the default.  */
+  if (width_source == SVE_SCALABLE)
+    return default_estimated_poly_value (val);
+
+  HOST_WIDE_INT over_128 = width_source - 128;
+  return val.coeffs[0] + val.coeffs[1] * over_128 / 128;
+}
+
 /* Target-specific selftests.  */
 
 #if CHECKING_P
@@ -18348,6 +18382,9 @@ aarch64_libgcc_floating_mode_supported_p
 #undef TARGET_SPECULATION_SAFE_VALUE
 #define TARGET_SPECULATION_SAFE_VALUE aarch64_speculation_safe_value
 
+#undef TARGET_ESTIMATED_POLY_VALUE
+#define TARGET_ESTIMATED_POLY_VALUE aarch64_estimated_poly_value
+
 #if CHECKING_P
 #undef TARGET_RUN_TARGET_SELFTESTS
 #define TARGET_RUN_TARGET_SELFTESTS selftest::aarch64_run_selftests