Hexagon (target/hexagon) make VyV operands use a unique temp

VyV operand is only used in the vshuff and vdeal instructions.  These
instructions write to both VyV and VxV operands.  In the case where
both operands are the same register, we need a separate location for
VyV.  We use the existing vtmp field in CPUHexagonState.

Test case added in tests/tcg/hexagon/hvx_misc.c

Signed-off-by: Taylor Simpson <tsimpson@quicinc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220718230320.24444-2-tsimpson@quicinc.com>

2 files changed, 49 insertions, 5 deletions

diff --git a/target/hexagon/gen_tcg_funcs.py b/target/hexagon/gen_tcg_funcs.py
index 1fd9de95d5..d72c689ad7 100755
--- a/target/hexagon/gen_tcg_funcs.py
+++ b/target/hexagon/gen_tcg_funcs.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 
 ##
-##  Copyright(c) 2019-2021 Qualcomm Innovation Center, Inc. All Rights Reserved.
+##  Copyright(c) 2019-2022 Qualcomm Innovation Center, Inc. All Rights Reserved.
 ##
 ##  This program is free software; you can redistribute it and/or modify
 ##  it under the terms of the GNU General Public License as published by
@@ -164,7 +164,9 @@ def genptr_decl(f, tag, regtype, regid, regno):
                 (regtype, regid, regno))
             f.write("    const intptr_t %s%sV_off =\n" % \
                 (regtype, regid))
-            if (hex_common.is_tmp_result(tag)):
+            if (regid == "y"):
+                f.write("        offsetof(CPUHexagonState, vtmp);\n")
+            elif (hex_common.is_tmp_result(tag)):
                 f.write("        ctx_tmp_vreg_off(ctx, %s%sN, 1, true);\n" % \
                     (regtype, regid))
             else:
@@ -379,9 +381,6 @@ def genptr_src_read(f, tag, regtype, regid):
             f.write("        vreg_src_off(ctx, %s%sN),\n" % \
                              (regtype, regid))
             f.write("        sizeof(MMVector), sizeof(MMVector));\n")
-            if (not hex_common.skip_qemu_helper(tag)):
-                f.write("    tcg_gen_addi_ptr(%s%sV, cpu_env, %s%sV_off);\n" % \
-                                 (regtype, regid, regtype, regid))
         else:
             print("Bad register parse: ", regtype, regid)
     elif (regtype == "Q"):
diff --git a/tests/tcg/hexagon/hvx_misc.c b/tests/tcg/hexagon/hvx_misc.c
index b896f5897e..6e2c9ab3cd 100644
--- a/tests/tcg/hexagon/hvx_misc.c
+++ b/tests/tcg/hexagon/hvx_misc.c
@@ -498,6 +498,49 @@ static void test_vsubuwsat_dv(void)
     check_output_w(__LINE__, 2);
 }
 
+static void test_vshuff(void)
+{
+    /* Test that vshuff works when the two operands are the same register */
+    const uint32_t splat = 0x089be55c;
+    const uint32_t shuff = 0x454fa926;
+    MMVector v0, v1;
+
+    memset(expect, 0x12, sizeof(MMVector));
+    memset(output, 0x34, sizeof(MMVector));
+
+    asm volatile("v25 = vsplat(%0)\n\t"
+                 "vshuff(v25, v25, %1)\n\t"
+                 "vmem(%2 + #0) = v25\n\t"
+                 : /* no outputs */
+                 : "r"(splat), "r"(shuff), "r"(output)
+                 : "v25", "memory");
+
+    /*
+     * The semantics of Hexagon are the operands are pass-by-value, so create
+     * two copies of the vsplat result.
+     */
+    for (int i = 0; i < MAX_VEC_SIZE_BYTES / 4; i++) {
+        v0.uw[i] = splat;
+        v1.uw[i] = splat;
+    }
+    /* Do the vshuff operation */
+    for (int offset = 1; offset < MAX_VEC_SIZE_BYTES; offset <<= 1) {
+        if (shuff & offset) {
+            for (int k = 0; k < MAX_VEC_SIZE_BYTES; k++) {
+                if (!(k & offset)) {
+                    uint8_t tmp = v0.ub[k];
+                    v0.ub[k] = v1.ub[k + offset];
+                    v1.ub[k + offset] = tmp;
+                }
+            }
+        }
+    }
+    /* Put the result in the expect buffer for verification */
+    expect[0] = v1;
+
+    check_output_b(__LINE__, 1);
+}
+
 int main()
 {
     init_buffers();
@@ -533,6 +576,8 @@ int main()
     test_vadduwsat();
     test_vsubuwsat_dv();
 
+    test_vshuff();
+
     puts(err ? "FAIL" : "PASS");
     return err ? 1 : 0;
 }