[gcc r14-5769] DSE: Allow vector type for get_stored_val when read < store

[gcc r14-5769] DSE: Allow vector type for get_stored_val when read < store

[Pan Li]

https://gcc.gnu.org/g:990769a343f090088f5025ad233f88824b2c6263

commit r14-5769-g990769a343f090088f5025ad233f88824b2c6263
Author: Pan Li <pan2.li@intel.com>
Date:   Mon Nov 13 11:22:37 2023 +0800

    DSE: Allow vector type for get_stored_val when read < store
    
    Update in v4:
    * Merge upstream and removed some independent changes.
    
    Update in v3:
    * Take known_le instead of known_lt for vector size.
    * Return NULL_RTX when gap is not equal 0 and not constant.
    
    Update in v2:
    * Move vector type support to get_stored_val.
    
    Original log:
    
    This patch would like to allow the vector mode in the
    get_stored_val in the DSE. It is valid for the read
    rtx if and only if the read bitsize is less than the
    stored bitsize.
    
    Given below example code with
    --param=riscv-autovec-preference=fixed-vlmax.
    
    vuint8m1_t test () {
      uint8_t arr[32] = {
        1, 2, 7, 1, 3, 4, 5, 3, 1, 0, 1, 2, 4, 4, 9, 9,
        1, 2, 7, 1, 3, 4, 5, 3, 1, 0, 1, 2, 4, 4, 9, 9,
      };
    
      return __riscv_vle8_v_u8m1(arr, 32);
    }
    
    Before this patch:
    test:
      lui     a5,%hi(.LANCHOR0)
      addi    sp,sp,-32
      addi    a5,a5,%lo(.LANCHOR0)
      li      a3,32
      vl2re64.v       v2,0(a5)
      vsetvli zero,a3,e8,m1,ta,ma
      vs2r.v  v2,0(sp)             <== Unnecessary store to stack
      vle8.v  v1,0(sp)             <== Ditto
      vs1r.v  v1,0(a0)
      addi    sp,sp,32
      jr      ra
    
    After this patch:
    test:
      lui     a5,%hi(.LANCHOR0)
      addi    a5,a5,%lo(.LANCHOR0)
      li      a4,32
      addi    sp,sp,-32
      vsetvli zero,a4,e8,m1,ta,ma
      vle8.v  v1,0(a5)
      vs1r.v  v1,0(a0)
      addi    sp,sp,32
      jr      ra
    
    Below tests are passed within this patch:
    * The risc-v regression test.
    * The x86 bootstrap and regression test.
    * The aarch64 regression test.
    
            PR target/111720
    
    gcc/ChangeLog:
    
            * dse.cc (get_stored_val): Allow vector mode if read size is
            less than or equal to stored size.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/riscv/rvv/base/pr111720-0.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-1.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-10.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-2.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-3.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-4.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-5.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-6.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-7.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-8.c: New test.
            * gcc.target/riscv/rvv/base/pr111720-9.c: New test.
    
    Signed-off-by: Pan Li <pan2.li@intel.com>

Diff:
---
 gcc/dse.cc                                          |  9 ++++++++-
 .../gcc.target/riscv/rvv/base/pr111720-0.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-1.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-10.c         | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-2.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-3.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-4.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-5.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-6.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-7.c          | 21 +++++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-8.c          | 18 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr111720-9.c          | 15 +++++++++++++++
 12 files changed, 206 insertions(+), 1 deletion(-)

diff --git a/gcc/dse.cc b/gcc/dse.cc
index 1a85dae1f8c..40c4c29d07e 100644
--- a/gcc/dse.cc
+++ b/gcc/dse.cc
@@ -1900,8 +1900,11 @@ get_stored_val (store_info *store_info, machine_mode read_mode,
   else
     gap = read_offset - store_info->offset;
 
-  if (gap.is_constant () && maybe_ne (gap, 0))
+  if (maybe_ne (gap, 0))
     {
+      if (!gap.is_constant ())
+	return NULL_RTX;
+
       poly_int64 shift = gap * BITS_PER_UNIT;
       poly_int64 access_size = GET_MODE_SIZE (read_mode) + gap;
       read_reg = find_shift_sequence (access_size, store_info, read_mode,
@@ -1940,6 +1943,10 @@ get_stored_val (store_info *store_info, machine_mode read_mode,
 	       || GET_MODE_CLASS (read_mode) != GET_MODE_CLASS (store_mode)))
     read_reg = extract_low_bits (read_mode, store_mode,
 				 copy_rtx (store_info->const_rhs));
+  else if (VECTOR_MODE_P (read_mode) && VECTOR_MODE_P (store_mode)
+    && known_le (GET_MODE_BITSIZE (read_mode), GET_MODE_BITSIZE (store_mode))
+    && targetm.modes_tieable_p (read_mode, store_mode))
+    read_reg = gen_lowpart (read_mode, copy_rtx (store_info->rhs));
   else
     read_reg = extract_low_bits (read_mode, store_mode,
 				 copy_rtx (store_info->rhs));
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-0.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-0.c
new file mode 100644
index 00000000000..a61e94a6d98
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-0.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8m1_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8m1(arr, 32);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-1.c
new file mode 100644
index 00000000000..46efd7379ac
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-1.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8m2_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8m2(arr, 32);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[09]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-10.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-10.c
new file mode 100644
index 00000000000..8bebac219a6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-10.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vbool4_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vlm_v_b4(arr, 32);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-2.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-2.c
new file mode 100644
index 00000000000..47e4243e02e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-2.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8m1_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8m1(arr, 16);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-3.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-3.c
new file mode 100644
index 00000000000..5331e547ed3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-3.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8m2_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8m2(arr, 8);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[09]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-4.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-4.c
new file mode 100644
index 00000000000..0c728f93514
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-4.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8mf2_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8mf2(arr, 32);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-5.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-5.c
new file mode 100644
index 00000000000..ccfc40cd382
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-5.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8m2_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8m2(arr, 4);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[09]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-6.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-6.c
new file mode 100644
index 00000000000..ce7ddbb99b2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-6.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vuint8m8_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  return __riscv_vle8_v_u8m8(arr, 32);
+}
+
+/* { dg-final { scan-assembler-times {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} 1 } } */
+/* { dg-final { scan-assembler-times {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} 1 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-7.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-7.c
new file mode 100644
index 00000000000..ac0100a1211
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-7.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vbool8_t test () {
+  uint8_t arr[32] = {
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+    1, 2, 7, 1, 3, 4, 5, 3,
+    1, 0, 1, 2, 4, 4, 9, 9,
+  };
+
+  vuint8m1_t varr = __riscv_vle8_v_u8m1(arr, 32);
+  vuint8m1_t vand_m = __riscv_vand_vx_u8m1(varr, 1, 32);
+
+  return __riscv_vreinterpret_v_u8m1_b8(vand_m);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-8.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-8.c
new file mode 100644
index 00000000000..b7ebef80954
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-8.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vfloat32m1_t test () {
+  float arr[32] = {
+    1.0, 2.2, 7.8, 1.2, 3.3, 4.7, 5.5, 3.3,
+    1.0, 0.2, 1.8, 2.2, 4.3, 4.7, 9.5, 9.3,
+    1.0, 2.2, 7.8, 1.2, 3.3, 4.7, 5.5, 3.3,
+    1.0, 0.2, 1.8, 2.2, 4.3, 4.7, 9.5, 9.3,
+  };
+
+  return __riscv_vle32_v_f32m1(arr, 32);
+}
+
+/* { dg-final { scan-assembler-not {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
+/* { dg-final { scan-assembler-not {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-9.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-9.c
new file mode 100644
index 00000000000..21fed06d201
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr111720-9.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv -mabi=lp64d -ftree-vectorize --param=riscv-autovec-preference=fixed-vlmax -Wno-psabi" } */
+
+#include "riscv_vector.h"
+
+vfloat64m8_t test () {
+  double arr[8] = {
+    1.0, 2.2, 7.8, 1.2, 3.3, 4.7, 5.5, 3.3,
+  };
+
+  return __riscv_vle64_v_f64m8(arr, 4);
+}
+
+/* { dg-final { scan-assembler-times {vle[0-9]+\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} 1 } } */
+/* { dg-final { scan-assembler-times {vs[0-9]+r\.v\s+v[0-9]+,\s*[0-9]+\(sp\)} 1 } } */