[Qemu-devel] [PULL 108/130] target-ppc: Altivec 2.07: Change Bit Masks to Support 64-bit Rotates and Shifts

[Alexander Graf]

From: Tom Musta <address@hidden>

Existing code in the VROTATE, VSL and VSR macros for the Altivec rotate and 
shift
helpers uses a formula to compute a bit mask used to extract the rotate/shift
amount from the VRB register.  What is desired is:

    mask = (1 << (3 + log2(sizeof(element)))) - 1

but what is implemented is:

    mask = (1 << (3 + (sizeof(element)/2))) - 1

This produces correct answers when "element" is uint8_t, uint16_t or uint_32t.  
But
it breaks down when element is uint64_t.

This patch corrects the situation.  Since the mask is known at compile time, the
macros are changed to simply accept the mask as an argument.

Subsequent patches in this series will add double-word variants of rotates and
shifts and thus take advantage of this fix.

Signed-off-by: Tom Musta <address@hidden>
Signed-off-by: Alexander Graf <address@hidden>
---
 target-ppc/int_helper.c | 40 +++++++++++++++-------------------------
 1 file changed, 15 insertions(+), 25 deletions(-)

diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
index 56e8d9a..59b5a1f 100644
--- a/target-ppc/int_helper.c
+++ b/target-ppc/int_helper.c
@@ -1128,23 +1128,20 @@ VRFI(p, float_round_up)
 VRFI(z, float_round_to_zero)
 #undef VRFI
 
-#define VROTATE(suffix, element)                                        \
+#define VROTATE(suffix, element, mask)                                  \
     void helper_vrl##suffix(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)   \
     {                                                                   \
         int i;                                                          \
                                                                         \
         for (i = 0; i < ARRAY_SIZE(r->element); i++) {                  \
-            unsigned int mask = ((1 <<                                  \
-                                  (3 + (sizeof(a->element[0]) >> 1)))   \
-                                 - 1);                                  \
             unsigned int shift = b->element[i] & mask;                  \
             r->element[i] = (a->element[i] << shift) |                  \
                 (a->element[i] >> (sizeof(a->element[0]) * 8 - shift)); \
         }                                                               \
     }
-VROTATE(b, u8)
-VROTATE(h, u16)
-VROTATE(w, u32)
+VROTATE(b, u8, 0x7)
+VROTATE(h, u16, 0xF)
+VROTATE(w, u32, 0x1F)
 #undef VROTATE
 
 void helper_vrsqrtefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b)
@@ -1225,23 +1222,20 @@ VSHIFT(r, RIGHT)
 #undef LEFT
 #undef RIGHT
 
-#define VSL(suffix, element)                                            \
+#define VSL(suffix, element, mask)                                      \
     void helper_vsl##suffix(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)   \
     {                                                                   \
         int i;                                                          \
                                                                         \
         for (i = 0; i < ARRAY_SIZE(r->element); i++) {                  \
-            unsigned int mask = ((1 <<                                  \
-                                  (3 + (sizeof(a->element[0]) >> 1)))   \
-                                 - 1);                                  \
             unsigned int shift = b->element[i] & mask;                  \
                                                                         \
             r->element[i] = a->element[i] << shift;                     \
         }                                                               \
     }
-VSL(b, u8)
-VSL(h, u16)
-VSL(w, u32)
+VSL(b, u8, 0x7)
+VSL(h, u16, 0x0F)
+VSL(w, u32, 0x1F)
 #undef VSL
 
 void helper_vsldoi(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t shift)
@@ -1325,26 +1319,22 @@ VSPLTI(h, s16, int16_t)
 VSPLTI(w, s32, int32_t)
 #undef VSPLTI
 
-#define VSR(suffix, element)                                            \
+#define VSR(suffix, element, mask)                                      \
     void helper_vsr##suffix(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)   \
     {                                                                   \
         int i;                                                          \
                                                                         \
         for (i = 0; i < ARRAY_SIZE(r->element); i++) {                  \
-            unsigned int mask = ((1 <<                                  \
-                                  (3 + (sizeof(a->element[0]) >> 1)))   \
-                                 - 1);                                  \
             unsigned int shift = b->element[i] & mask;                  \
-                                                                        \
             r->element[i] = a->element[i] >> shift;                     \
         }                                                               \
     }
-VSR(ab, s8)
-VSR(ah, s16)
-VSR(aw, s32)
-VSR(b, u8)
-VSR(h, u16)
-VSR(w, u32)
+VSR(ab, s8, 0x7)
+VSR(ah, s16, 0xF)
+VSR(aw, s32, 0x1F)
+VSR(b, u8, 0x7)
+VSR(h, u16, 0xF)
+VSR(w, u32, 0x1F)
 #undef VSR
 
 void helper_vsro(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
-- 
1.8.1.4