target-arm: Move Neon VZIP to helper functions

Move the implementation of the Neon VUZP unzip instruction from inline
code to helper functions. (At 50+ TCG ops it was well over the
recommended limit for coding inline.) The helper implementations also
give the correct answers where the inline implementation did not.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

1 files changed, 92 insertions, 0 deletions

diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index 49f1b15945..bcc1b4ba1e 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -1787,3 +1787,95 @@ void HELPER(neon_unzip16)(CPUState *env, uint32_t rd, uint32_t rm)
     env->vfp.regs[rm] = make_float64(m0);
     env->vfp.regs[rd] = make_float64(d0);
 }
+
+void HELPER(neon_qzip8)(CPUState *env, uint32_t rd, uint32_t rm)
+{
+    uint64_t zm0 = float64_val(env->vfp.regs[rm]);
+    uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
+    uint64_t zd0 = float64_val(env->vfp.regs[rd]);
+    uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+    uint64_t d0 = ELEM(zd0, 0, 8) | (ELEM(zm0, 0, 8) << 8)
+        | (ELEM(zd0, 1, 8) << 16) | (ELEM(zm0, 1, 8) << 24)
+        | (ELEM(zd0, 2, 8) << 32) | (ELEM(zm0, 2, 8) << 40)
+        | (ELEM(zd0, 3, 8) << 48) | (ELEM(zm0, 3, 8) << 56);
+    uint64_t d1 = ELEM(zd0, 4, 8) | (ELEM(zm0, 4, 8) << 8)
+        | (ELEM(zd0, 5, 8) << 16) | (ELEM(zm0, 5, 8) << 24)
+        | (ELEM(zd0, 6, 8) << 32) | (ELEM(zm0, 6, 8) << 40)
+        | (ELEM(zd0, 7, 8) << 48) | (ELEM(zm0, 7, 8) << 56);
+    uint64_t m0 = ELEM(zd1, 0, 8) | (ELEM(zm1, 0, 8) << 8)
+        | (ELEM(zd1, 1, 8) << 16) | (ELEM(zm1, 1, 8) << 24)
+        | (ELEM(zd1, 2, 8) << 32) | (ELEM(zm1, 2, 8) << 40)
+        | (ELEM(zd1, 3, 8) << 48) | (ELEM(zm1, 3, 8) << 56);
+    uint64_t m1 = ELEM(zd1, 4, 8) | (ELEM(zm1, 4, 8) << 8)
+        | (ELEM(zd1, 5, 8) << 16) | (ELEM(zm1, 5, 8) << 24)
+        | (ELEM(zd1, 6, 8) << 32) | (ELEM(zm1, 6, 8) << 40)
+        | (ELEM(zd1, 7, 8) << 48) | (ELEM(zm1, 7, 8) << 56);
+    env->vfp.regs[rm] = make_float64(m0);
+    env->vfp.regs[rm + 1] = make_float64(m1);
+    env->vfp.regs[rd] = make_float64(d0);
+    env->vfp.regs[rd + 1] = make_float64(d1);
+}
+
+void HELPER(neon_qzip16)(CPUState *env, uint32_t rd, uint32_t rm)
+{
+    uint64_t zm0 = float64_val(env->vfp.regs[rm]);
+    uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
+    uint64_t zd0 = float64_val(env->vfp.regs[rd]);
+    uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+    uint64_t d0 = ELEM(zd0, 0, 16) | (ELEM(zm0, 0, 16) << 16)
+        | (ELEM(zd0, 1, 16) << 32) | (ELEM(zm0, 1, 16) << 48);
+    uint64_t d1 = ELEM(zd0, 2, 16) | (ELEM(zm0, 2, 16) << 16)
+        | (ELEM(zd0, 3, 16) << 32) | (ELEM(zm0, 3, 16) << 48);
+    uint64_t m0 = ELEM(zd1, 0, 16) | (ELEM(zm1, 0, 16) << 16)
+        | (ELEM(zd1, 1, 16) << 32) | (ELEM(zm1, 1, 16) << 48);
+    uint64_t m1 = ELEM(zd1, 2, 16) | (ELEM(zm1, 2, 16) << 16)
+        | (ELEM(zd1, 3, 16) << 32) | (ELEM(zm1, 3, 16) << 48);
+    env->vfp.regs[rm] = make_float64(m0);
+    env->vfp.regs[rm + 1] = make_float64(m1);
+    env->vfp.regs[rd] = make_float64(d0);
+    env->vfp.regs[rd + 1] = make_float64(d1);
+}
+
+void HELPER(neon_qzip32)(CPUState *env, uint32_t rd, uint32_t rm)
+{
+    uint64_t zm0 = float64_val(env->vfp.regs[rm]);
+    uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
+    uint64_t zd0 = float64_val(env->vfp.regs[rd]);
+    uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+    uint64_t d0 = ELEM(zd0, 0, 32) | (ELEM(zm0, 0, 32) << 32);
+    uint64_t d1 = ELEM(zd0, 1, 32) | (ELEM(zm0, 1, 32) << 32);
+    uint64_t m0 = ELEM(zd1, 0, 32) | (ELEM(zm1, 0, 32) << 32);
+    uint64_t m1 = ELEM(zd1, 1, 32) | (ELEM(zm1, 1, 32) << 32);
+    env->vfp.regs[rm] = make_float64(m0);
+    env->vfp.regs[rm + 1] = make_float64(m1);
+    env->vfp.regs[rd] = make_float64(d0);
+    env->vfp.regs[rd + 1] = make_float64(d1);
+}
+
+void HELPER(neon_zip8)(CPUState *env, uint32_t rd, uint32_t rm)
+{
+    uint64_t zm = float64_val(env->vfp.regs[rm]);
+    uint64_t zd = float64_val(env->vfp.regs[rd]);
+    uint64_t d0 = ELEM(zd, 0, 8) | (ELEM(zm, 0, 8) << 8)
+        | (ELEM(zd, 1, 8) << 16) | (ELEM(zm, 1, 8) << 24)
+        | (ELEM(zd, 2, 8) << 32) | (ELEM(zm, 2, 8) << 40)
+        | (ELEM(zd, 3, 8) << 48) | (ELEM(zm, 3, 8) << 56);
+    uint64_t m0 = ELEM(zd, 4, 8) | (ELEM(zm, 4, 8) << 8)
+        | (ELEM(zd, 5, 8) << 16) | (ELEM(zm, 5, 8) << 24)
+        | (ELEM(zd, 6, 8) << 32) | (ELEM(zm, 6, 8) << 40)
+        | (ELEM(zd, 7, 8) << 48) | (ELEM(zm, 7, 8) << 56);
+    env->vfp.regs[rm] = make_float64(m0);
+    env->vfp.regs[rd] = make_float64(d0);
+}
+
+void HELPER(neon_zip16)(CPUState *env, uint32_t rd, uint32_t rm)
+{
+    uint64_t zm = float64_val(env->vfp.regs[rm]);
+    uint64_t zd = float64_val(env->vfp.regs[rd]);
+    uint64_t d0 = ELEM(zd, 0, 16) | (ELEM(zm, 0, 16) << 16)
+        | (ELEM(zd, 1, 16) << 32) | (ELEM(zm, 1, 16) << 48);
+    uint64_t m0 = ELEM(zd, 2, 16) | (ELEM(zm, 2, 16) << 16)
+        | (ELEM(zd, 3, 16) << 32) | (ELEM(zm, 3, 16) << 48);
+    env->vfp.regs[rm] = make_float64(m0);
+    env->vfp.regs[rd] = make_float64(d0);
+}