Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-tcg-20220304' into staging

Reorder do_constant_folding_cond test to satisfy valgrind.
Fix value of MAX_OPC_PARAM_IARGS.
Add opcodes for vector nand, nor, eqv.
Support vector nand, nor, eqv on PPC and S390X hosts.
Support AVX512VL, AVX512BW, AVX512DQ, and AVX512VBMI2.

# gpg: Signature made Fri 04 Mar 2022 18:59:08 GMT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-tcg-20220304: (21 commits)
  tcg/i386: Implement bitsel for avx512
  tcg/i386: Implement more logical operations for avx512
  tcg/i386: Implement avx512 multiply
  tcg/i386: Implement avx512 min/max/abs
  tcg/i386: Expand scalar rotate with avx512 insns
  tcg/i386: Remove rotls_vec from tcg_target_op_def
  tcg/i386: Expand vector word rotate as avx512vbmi2 shift-double
  tcg/i386: Support avx512vbmi2 vector shift-double instructions
  tcg/i386: Implement avx512 variable rotate
  tcg/i386: Implement avx512 immediate rotate
  tcg/i386: Implement avx512 immediate sari shift
  tcg/i386: Implement avx512 scalar shift
  tcg/i386: Implement avx512 variable shifts
  tcg/i386: Use tcg_can_emit_vec_op in expand_vec_cmp_noinv
  tcg/i386: Add tcg_out_evex_opc
  tcg/i386: Detect AVX512
  tcg/s390x: Implement vector NAND, NOR, EQV
  tcg/ppc: Implement vector NAND, NOR, EQV
  tcg: Add opcodes for vector nand, nor, eqv
  tcg: Set MAX_OPC_PARAM_IARGS to 7
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 10 insertions, 10 deletions

diff --git a/tcg/optimize.c b/tcg/optimize.c
index e573000951..ae081ab29c 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -359,13 +359,13 @@ static uint64_t do_constant_folding_2(TCGOpcode op, uint64_t x, uint64_t y)
     CASE_OP_32_64_VEC(orc):
         return x | ~y;
 
-    CASE_OP_32_64(eqv):
+    CASE_OP_32_64_VEC(eqv):
         return ~(x ^ y);
 
-    CASE_OP_32_64(nand):
+    CASE_OP_32_64_VEC(nand):
         return ~(x & y);
 
-    CASE_OP_32_64(nor):
+    CASE_OP_32_64_VEC(nor):
         return ~(x | y);
 
     case INDEX_op_clz_i32:
@@ -552,10 +552,10 @@ static bool do_constant_folding_cond_eq(TCGCond c)
 static int do_constant_folding_cond(TCGType type, TCGArg x,
                                     TCGArg y, TCGCond c)
 {
-    uint64_t xv = arg_info(x)->val;
-    uint64_t yv = arg_info(y)->val;
-
     if (arg_is_const(x) && arg_is_const(y)) {
+        uint64_t xv = arg_info(x)->val;
+        uint64_t yv = arg_info(y)->val;
+
         switch (type) {
         case TCG_TYPE_I32:
             return do_constant_folding_cond_32(xv, yv, c);
@@ -567,7 +567,7 @@ static int do_constant_folding_cond(TCGType type, TCGArg x,
         }
     } else if (args_are_copies(x, y)) {
         return do_constant_folding_cond_eq(c);
-    } else if (arg_is_const(y) && yv == 0) {
+    } else if (arg_is_const(y) && arg_info(y)->val == 0) {
         switch (c) {
         case TCG_COND_LTU:
             return 0;
@@ -2119,7 +2119,7 @@ void tcg_optimize(TCGContext *s)
         case INDEX_op_dup2_vec:
             done = fold_dup2(&ctx, op);
             break;
-        CASE_OP_32_64(eqv):
+        CASE_OP_32_64_VEC(eqv):
             done = fold_eqv(&ctx, op);
             break;
         CASE_OP_32_64(extract):
@@ -2170,13 +2170,13 @@ void tcg_optimize(TCGContext *s)
         CASE_OP_32_64(mulu2):
             done = fold_multiply2(&ctx, op);
             break;
-        CASE_OP_32_64(nand):
+        CASE_OP_32_64_VEC(nand):
             done = fold_nand(&ctx, op);
             break;
         CASE_OP_32_64(neg):
             done = fold_neg(&ctx, op);
             break;
-        CASE_OP_32_64(nor):
+        CASE_OP_32_64_VEC(nor):
             done = fold_nor(&ctx, op);
             break;
         CASE_OP_32_64_VEC(not):