[PATCH v3 12/34] target/arm/tcg: Move NEON helpers to neon_helper.c

[Philippe Mathieu-Daudé]

Move various NEON helpers to the well named neon_helper.c.

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
 target/arm/tcg/helper-a64.c  |  80 --------------------------
 target/arm/tcg/neon_helper.c | 106 +++++++++++++++++++++++++++++++++++
 target/arm/tcg/op_helper.c   |  22 --------
 3 files changed, 106 insertions(+), 102 deletions(-)

diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index c43f22e7d4..6312238676 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -93,25 +93,6 @@ void HELPER(msr_i_daifclear)(CPUARMState *env, uint32_t imm)
     arm_rebuild_hflags(env);
 }
 
-/* 64bit/double versions of the neon float compare functions */
-uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp)
-{
-    float_status *fpst = fpstp;
-    return -float64_eq_quiet(a, b, fpst);
-}
-
-uint64_t HELPER(neon_cge_f64)(float64 a, float64 b, void *fpstp)
-{
-    float_status *fpst = fpstp;
-    return -float64_le(b, a, fpst);
-}
-
-uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp)
-{
-    float_status *fpst = fpstp;
-    return -float64_lt(b, a, fpst);
-}
-
 /* Reciprocal step and sqrt step. Note that unlike the A32/T32
  * versions, these do a fully fused multiply-add or
  * multiply-add-and-halve.
@@ -207,67 +188,6 @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void 
*fpstp)
     return float64_muladd(a, b, float64_three, float_muladd_halve_result, 
fpst);
 }
 
-/* Pairwise long add: add pairs of adjacent elements into
- * double-width elements in the result (eg _s8 is an 8x8->16 op)
- */
-uint64_t HELPER(neon_addlp_s8)(uint64_t a)
-{
-    uint64_t nsignmask = 0x0080008000800080ULL;
-    uint64_t wsignmask = 0x8000800080008000ULL;
-    uint64_t elementmask = 0x00ff00ff00ff00ffULL;
-    uint64_t tmp1, tmp2;
-    uint64_t res, signres;
-
-    /* Extract odd elements, sign extend each to a 16 bit field */
-    tmp1 = a & elementmask;
-    tmp1 ^= nsignmask;
-    tmp1 |= wsignmask;
-    tmp1 = (tmp1 - nsignmask) ^ wsignmask;
-    /* Ditto for the even elements */
-    tmp2 = (a >> 8) & elementmask;
-    tmp2 ^= nsignmask;
-    tmp2 |= wsignmask;
-    tmp2 = (tmp2 - nsignmask) ^ wsignmask;
-
-    /* calculate the result by summing bits 0..14, 16..22, etc,
-     * and then adjusting the sign bits 15, 23, etc manually.
-     * This ensures the addition can't overflow the 16 bit field.
-     */
-    signres = (tmp1 ^ tmp2) & wsignmask;
-    res = (tmp1 & ~wsignmask) + (tmp2 & ~wsignmask);
-    res ^= signres;
-
-    return res;
-}
-
-uint64_t HELPER(neon_addlp_u8)(uint64_t a)
-{
-    uint64_t tmp;
-
-    tmp = a & 0x00ff00ff00ff00ffULL;
-    tmp += (a >> 8) & 0x00ff00ff00ff00ffULL;
-    return tmp;
-}
-
-uint64_t HELPER(neon_addlp_s16)(uint64_t a)
-{
-    int32_t reslo, reshi;
-
-    reslo = (int32_t)(int16_t)a + (int32_t)(int16_t)(a >> 16);
-    reshi = (int32_t)(int16_t)(a >> 32) + (int32_t)(int16_t)(a >> 48);
-
-    return (uint32_t)reslo | (((uint64_t)reshi) << 32);
-}
-
-uint64_t HELPER(neon_addlp_u16)(uint64_t a)
-{
-    uint64_t tmp;
-
-    tmp = a & 0x0000ffff0000ffffULL;
-    tmp += (a >> 16) & 0x0000ffff0000ffffULL;
-    return tmp;
-}
-
 /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */
 uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp)
 {
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index bc6c4a54e9..cd668eb43a 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -1738,3 +1738,109 @@ void HELPER(neon_zip16)(void *vd, void *vm)
     rm[0] = m0;
     rd[0] = d0;
 }
+
+uint64_t HELPER(neon_tbl)(CPUARMState *env, uint32_t desc,
+                          uint64_t ireg, uint64_t def)
+{
+    uint64_t tmp, val = 0;
+    uint32_t maxindex = ((desc & 3) + 1) * 8;
+    uint32_t base_reg = desc >> 2;
+    uint32_t shift, index, reg;
+
+    for (shift = 0; shift < 64; shift += 8) {
+        index = (ireg >> shift) & 0xff;
+        if (index < maxindex) {
+            reg = base_reg + (index >> 3);
+            tmp = *aa32_vfp_dreg(env, reg);
+            tmp = ((tmp >> ((index & 7) << 3)) & 0xff) << shift;
+        } else {
+            tmp = def & (0xffull << shift);
+        }
+        val |= tmp;
+    }
+    return val;
+}
+
+#ifdef TARGET_AARCH64
+
+/* Pairwise long add: add pairs of adjacent elements into
+ * double-width elements in the result (eg _s8 is an 8x8->16 op)
+ */
+uint64_t HELPER(neon_addlp_s8)(uint64_t a)
+{
+    uint64_t nsignmask = 0x0080008000800080ULL;
+    uint64_t wsignmask = 0x8000800080008000ULL;
+    uint64_t elementmask = 0x00ff00ff00ff00ffULL;
+    uint64_t tmp1, tmp2;
+    uint64_t res, signres;
+
+    /* Extract odd elements, sign extend each to a 16 bit field */
+    tmp1 = a & elementmask;
+    tmp1 ^= nsignmask;
+    tmp1 |= wsignmask;
+    tmp1 = (tmp1 - nsignmask) ^ wsignmask;
+    /* Ditto for the even elements */
+    tmp2 = (a >> 8) & elementmask;
+    tmp2 ^= nsignmask;
+    tmp2 |= wsignmask;
+    tmp2 = (tmp2 - nsignmask) ^ wsignmask;
+
+    /* calculate the result by summing bits 0..14, 16..22, etc,
+     * and then adjusting the sign bits 15, 23, etc manually.
+     * This ensures the addition can't overflow the 16 bit field.
+     */
+    signres = (tmp1 ^ tmp2) & wsignmask;
+    res = (tmp1 & ~wsignmask) + (tmp2 & ~wsignmask);
+    res ^= signres;
+
+    return res;
+}
+
+uint64_t HELPER(neon_addlp_u8)(uint64_t a)
+{
+    uint64_t tmp;
+
+    tmp = a & 0x00ff00ff00ff00ffULL;
+    tmp += (a >> 8) & 0x00ff00ff00ff00ffULL;
+    return tmp;
+}
+
+uint64_t HELPER(neon_addlp_s16)(uint64_t a)
+{
+    int32_t reslo, reshi;
+
+    reslo = (int32_t)(int16_t)a + (int32_t)(int16_t)(a >> 16);
+    reshi = (int32_t)(int16_t)(a >> 32) + (int32_t)(int16_t)(a >> 48);
+
+    return (uint32_t)reslo | (((uint64_t)reshi) << 32);
+}
+
+uint64_t HELPER(neon_addlp_u16)(uint64_t a)
+{
+    uint64_t tmp;
+
+    tmp = a & 0x0000ffff0000ffffULL;
+    tmp += (a >> 16) & 0x0000ffff0000ffffULL;
+    return tmp;
+}
+
+/* 64bit/double versions of the neon float compare functions */
+uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    return -float64_eq_quiet(a, b, fpst);
+}
+
+uint64_t HELPER(neon_cge_f64)(float64 a, float64 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    return -float64_le(b, a, fpst);
+}
+
+uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    return -float64_lt(b, a, fpst);
+}
+
+#endif /* TARGET_AARCH64 */
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index 3baf8004f6..70a9c37b74 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -82,28 +82,6 @@ void raise_exception_ra(CPUARMState *env, uint32_t excp, 
uint32_t syndrome,
     raise_exception(env, excp, syndrome, target_el);
 }
 
-uint64_t HELPER(neon_tbl)(CPUARMState *env, uint32_t desc,
-                          uint64_t ireg, uint64_t def)
-{
-    uint64_t tmp, val = 0;
-    uint32_t maxindex = ((desc & 3) + 1) * 8;
-    uint32_t base_reg = desc >> 2;
-    uint32_t shift, index, reg;
-
-    for (shift = 0; shift < 64; shift += 8) {
-        index = (ireg >> shift) & 0xff;
-        if (index < maxindex) {
-            reg = base_reg + (index >> 3);
-            tmp = *aa32_vfp_dreg(env, reg);
-            tmp = ((tmp >> ((index & 7) << 3)) & 0xff) << shift;
-        } else {
-            tmp = def & (0xffull << shift);
-        }
-        val |= tmp;
-    }
-    return val;
-}
-
 void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue)
 {
     /*
-- 
2.38.1