diff mbox series

[1/4] tcg: Don't free vector results

Message ID 20230831025729.1194388-2-richard.henderson@linaro.org
State New
Headers show
Series tcg: Optimize loads and stores to env | expand

Commit Message

Richard Henderson Aug. 31, 2023, 2:57 a.m. UTC 
Avoid reusing vector temporaries so that we may re-use them
when propagating stores to loads.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/tcg-op-gvec.c | 39 ++++++---------------------------------
 1 file changed, 6 insertions(+), 33 deletions(-)
diff mbox series

Patch

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index e260a07c61..f5cfd9bf99 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -561,7 +561,6 @@  static void do_dup(unsigned vece, uint32_t dofs, uint32_t oprsz,
             tcg_gen_dupi_vec(vece, t_vec, in_c);
         }
         do_dup_store(type, dofs, oprsz, maxsz, t_vec);
-        tcg_temp_free_vec(t_vec);
         return;
     }
 
@@ -1036,8 +1035,6 @@  static void expand_2_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         fni(vece, t1, t0);
         tcg_gen_st_vec(t1, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t0);
-    tcg_temp_free_vec(t1);
 }
 
 /* Expand OPSZ bytes worth of two-vector operands and an immediate operand
@@ -1059,8 +1056,6 @@  static void expand_2i_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         fni(vece, t1, t0, c);
         tcg_gen_st_vec(t1, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t0);
-    tcg_temp_free_vec(t1);
 }
 
 static void expand_2s_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
@@ -1081,8 +1076,6 @@  static void expand_2s_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         }
         tcg_gen_st_vec(t1, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t0);
-    tcg_temp_free_vec(t1);
 }
 
 /* Expand OPSZ bytes worth of three-operand operations using host vectors.  */
@@ -1105,9 +1098,6 @@  static void expand_3_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         fni(vece, t2, t0, t1);
         tcg_gen_st_vec(t2, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t2);
-    tcg_temp_free_vec(t1);
-    tcg_temp_free_vec(t0);
 }
 
 /*
@@ -1134,9 +1124,6 @@  static void expand_3i_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         fni(vece, t2, t0, t1, c);
         tcg_gen_st_vec(t2, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t0);
-    tcg_temp_free_vec(t1);
-    tcg_temp_free_vec(t2);
 }
 
 /* Expand OPSZ bytes worth of four-operand operations using host vectors.  */
@@ -1162,10 +1149,6 @@  static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
             tcg_gen_st_vec(t1, cpu_env, aofs + i);
         }
     }
-    tcg_temp_free_vec(t3);
-    tcg_temp_free_vec(t2);
-    tcg_temp_free_vec(t1);
-    tcg_temp_free_vec(t0);
 }
 
 /*
@@ -1191,10 +1174,6 @@  static void expand_4i_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
         fni(vece, t0, t1, t2, t3, c);
         tcg_gen_st_vec(t0, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t3);
-    tcg_temp_free_vec(t2);
-    tcg_temp_free_vec(t1);
-    tcg_temp_free_vec(t0);
 }
 
 /* Expand a vector two-operand operation.  */
@@ -1732,7 +1711,6 @@  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
             TCGv_vec t_vec = tcg_temp_new_vec(type);
             tcg_gen_dup_mem_vec(vece, t_vec, cpu_env, aofs);
             do_dup_store(type, dofs, oprsz, maxsz, t_vec);
-            tcg_temp_free_vec(t_vec);
         } else if (vece <= MO_32) {
             TCGv_i32 in = tcg_temp_ebb_new_i32();
             switch (vece) {
@@ -1766,7 +1744,6 @@  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
             for (i = (aofs == dofs) * 16; i < oprsz; i += 16) {
                 tcg_gen_st_vec(in, cpu_env, dofs + i);
             }
-            tcg_temp_free_vec(in);
         } else {
             TCGv_i64 in0 = tcg_temp_ebb_new_i64();
             TCGv_i64 in1 = tcg_temp_ebb_new_i64();
@@ -1796,7 +1773,6 @@  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
             for (i = (aofs == dofs) * 32; i < oprsz; i += 32) {
                 tcg_gen_st_vec(in, cpu_env, dofs + i);
             }
-            tcg_temp_free_vec(in);
         } else if (TCG_TARGET_HAS_v128) {
             TCGv_vec in0 = tcg_temp_new_vec(TCG_TYPE_V128);
             TCGv_vec in1 = tcg_temp_new_vec(TCG_TYPE_V128);
@@ -1807,8 +1783,6 @@  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
                 tcg_gen_st_vec(in0, cpu_env, dofs + i);
                 tcg_gen_st_vec(in1, cpu_env, dofs + i + 16);
             }
-            tcg_temp_free_vec(in0);
-            tcg_temp_free_vec(in1);
         } else {
             TCGv_i64 in[4];
             int j;
@@ -3137,14 +3111,14 @@  static void expand_2sh_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
                            void (*fni)(unsigned, TCGv_vec, TCGv_vec, TCGv_i32))
 {
     TCGv_vec t0 = tcg_temp_new_vec(type);
+    TCGv_vec t1 = tcg_temp_new_vec(type);
     uint32_t i;
 
     for (i = 0; i < oprsz; i += tysz) {
         tcg_gen_ld_vec(t0, cpu_env, aofs + i);
-        fni(vece, t0, t0, shift);
-        tcg_gen_st_vec(t0, cpu_env, dofs + i);
+        fni(vece, t1, t0, shift);
+        tcg_gen_st_vec(t1, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t0);
 }
 
 static void
@@ -3722,16 +3696,15 @@  static void expand_cmp_vec(unsigned vece, uint32_t dofs, uint32_t aofs,
 {
     TCGv_vec t0 = tcg_temp_new_vec(type);
     TCGv_vec t1 = tcg_temp_new_vec(type);
+    TCGv_vec t2 = tcg_temp_new_vec(type);
     uint32_t i;
 
     for (i = 0; i < oprsz; i += tysz) {
         tcg_gen_ld_vec(t0, cpu_env, aofs + i);
         tcg_gen_ld_vec(t1, cpu_env, bofs + i);
-        tcg_gen_cmp_vec(cond, vece, t0, t0, t1);
-        tcg_gen_st_vec(t0, cpu_env, dofs + i);
+        tcg_gen_cmp_vec(cond, vece, t2, t0, t1);
+        tcg_gen_st_vec(t2, cpu_env, dofs + i);
     }
-    tcg_temp_free_vec(t1);
-    tcg_temp_free_vec(t0);
 }
 
 void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs,