From: Richard Henderson <richard.henderson@linaro.org>

This instruction has f32 as source1, which alters the
decoding of the register number, which means we've been
passing the wrong data for odd register numbers.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20240502165528.244004-4-richard.henderson@linaro.org>
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
---
 target/sparc/helper.h     |  2 +-
 target/sparc/translate.c  | 21 ++++++++++++++++++++-
 target/sparc/vis_helper.c |  9 +++++----
 3 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/target/sparc/helper.h b/target/sparc/helper.h
index 57ab755ffd..27dc604cac 100644
--- a/target/sparc/helper.h
+++ b/target/sparc/helper.h
@@ -95,7 +95,7 @@ DEF_HELPER_FLAGS_2(fdtox, TCG_CALL_NO_WG, s64, env, f64)
 DEF_HELPER_FLAGS_2(fqtox, TCG_CALL_NO_WG, s64, env, i128)
 
 DEF_HELPER_FLAGS_2(fpmerge, TCG_CALL_NO_RWG_SE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(fmul8x16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(fmul8x16, TCG_CALL_NO_RWG_SE, i64, i32, i64)
 DEF_HELPER_FLAGS_2(fmul8x16al, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(fmul8x16au, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(fmul8sux16, TCG_CALL_NO_RWG_SE, i64, i64, i64)
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index dfcfe855a1..c4adc148d2 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -4583,6 +4583,26 @@ TRANS(FSUBs, ALL, do_env_fff, a, gen_helper_fsubs)
 TRANS(FMULs, ALL, do_env_fff, a, gen_helper_fmuls)
 TRANS(FDIVs, ALL, do_env_fff, a, gen_helper_fdivs)
 
+static bool do_dfd(DisasContext *dc, arg_r_r_r *a,
+                   void (*func)(TCGv_i64, TCGv_i32, TCGv_i64))
+{
+    TCGv_i64 dst, src2;
+    TCGv_i32 src1;
+
+    if (gen_trap_ifnofpu(dc)) {
+        return true;
+    }
+
+    dst = gen_dest_fpr_D(dc, a->rd);
+    src1 = gen_load_fpr_F(dc, a->rs1);
+    src2 = gen_load_fpr_D(dc, a->rs2);
+    func(dst, src1, src2);
+    gen_store_fpr_D(dc, a->rd, dst);
+    return advance_pc(dc);
+}
+
+TRANS(FMUL8x16, VIS1, do_dfd, a, gen_helper_fmul8x16)
+
 static bool do_ddd(DisasContext *dc, arg_r_r_r *a,
                    void (*func)(TCGv_i64, TCGv_i64, TCGv_i64))
 {
@@ -4600,7 +4620,6 @@ static bool do_ddd(DisasContext *dc, arg_r_r_r *a,
     return advance_pc(dc);
 }
 
-TRANS(FMUL8x16, VIS1, do_ddd, a, gen_helper_fmul8x16)
 TRANS(FMUL8x16AU, VIS1, do_ddd, a, gen_helper_fmul8x16au)
 TRANS(FMUL8x16AL, VIS1, do_ddd, a, gen_helper_fmul8x16al)
 TRANS(FMUL8SUx16, VIS1, do_ddd, a, gen_helper_fmul8sux16)
diff --git a/target/sparc/vis_helper.c b/target/sparc/vis_helper.c
index db2e6dd6c1..7728ffe9c6 100644
--- a/target/sparc/vis_helper.c
+++ b/target/sparc/vis_helper.c
@@ -94,16 +94,17 @@ uint64_t helper_fpmerge(uint64_t src1, uint64_t src2)
     return d.ll;
 }
 
-uint64_t helper_fmul8x16(uint64_t src1, uint64_t src2)
+uint64_t helper_fmul8x16(uint32_t src1, uint64_t src2)
 {
-    VIS64 s, d;
+    VIS64 d;
+    VIS32 s;
     uint32_t tmp;
 
-    s.ll = src1;
+    s.l = src1;
     d.ll = src2;
 
 #define PMUL(r)                                                 \
-    tmp = (int32_t)d.VIS_SW64(r) * (int32_t)s.VIS_B64(r);       \
+    tmp = (int32_t)d.VIS_SW64(r) * (int32_t)s.VIS_B32(r);       \
     if ((tmp & 0xff) > 0x7f) {                                  \
         tmp += 0x100;                                           \
     }                                                           \
-- 
2.39.2