Hi Richard,
On 28/01/15 14:14, Richard Biener wrote:
This fixes PR64829 where widening shift pattern detection fails to
verify the widening operation is used only in the shift.
Bootstrap and regtest running on x86_64-unknown-linux-gnu.
This patch causes a testsuite fail on an arm-none-eabi cross:
FAIL: gcc.dg/vect/vect-widen-shift-u8.c scan-tree-dump-times vect
"vect_recog_widen_shift_pattern: detected" 2
FAIL: gcc.dg/vect/vect-widen-shift-u8.c -flto -ffat-lto-objects
scan-tree-dump-times vect "vect_recog_widen_shift_pattern: detected" 2
The widen_shift pattern doesn't get recognised although the loop is
still vectorised.
Is this something we can avoid?
Or should the test be adjusted?
Thanks,
Kyrill
Richard.
2015-01-28 Richard Biener <rguent...@suse.de>
PR tree-optimization/64829
* tree-vect-patterns.c (vect_recog_widen_shift_pattern): Check
that the shift operand has a single use only.
* gcc.dg/vect/pr64829.c: New testcase.
Index: gcc/tree-vect-patterns.c
===================================================================
--- gcc/tree-vect-patterns.c (revision 220205)
+++ gcc/tree-vect-patterns.c (working copy)
@@ -1732,9 +1732,11 @@ vect_recog_widen_shift_pattern (vec<gimp
if (TREE_CODE (oprnd0) != SSA_NAME || TREE_CODE (oprnd1) != INTEGER_CST)
return NULL;
- /* Check operand 0: it has to be defined by a type promotion. */
- if (!type_conversion_p (oprnd0, last_stmt, false, &half_type0, &def_stmt0,
- &promotion)
+ /* Check operand 0: it has to be defined by a type promotion and it
+ should be only used by the shift. */
+ if (!has_single_use (oprnd0)
+ || !type_conversion_p (oprnd0, last_stmt, false, &half_type0, &def_stmt0,
+ &promotion)
|| !promotion)
return NULL;
Index: gcc/testsuite/gcc.dg/vect/pr64829.c
===================================================================
--- gcc/testsuite/gcc.dg/vect/pr64829.c (revision 0)
+++ gcc/testsuite/gcc.dg/vect/pr64829.c (working copy)
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+
+typedef unsigned char Uint8;
+typedef int Sint32;
+typedef unsigned int Uint32;
+
+typedef union RMColorDataRef
+{
+ Uint8* data8;
+} RMColorDataRef;
+
+typedef struct RMColorData
+{
+ Uint32 dataCount;
+ RMColorDataRef dataRef;
+} RMColorData;
+
+typedef struct RMColorTable
+{
+ Uint8 dataCompsOut;
+ RMColorDataRef dataRef;
+} RMColorTable;
+
+int fail ( const RMColorData * pInColor,
+ RMColorData * pOutColor,
+ const RMColorTable * pColorTable )
+{
+ Uint32 comp;
+ Uint8 nCompOut;
+
+ Sint32 result;
+
+ Uint32 interpFrac1, interpFrac2, interpFrac3;
+ Sint32 val0, val1, val2, val3;
+
+ Uint8 * pOut;
+
+ const Uint8 * pClutData;
+ const Uint8 * pCornerPoint0;
+
+ Uint8 lastOut[((8) > (4) ? (8) : (4))];
+
+ pOut = pOutColor->dataRef.data8;
+ pClutData = pColorTable->dataRef.data8;
+
+ nCompOut = pColorTable->dataCompsOut;
+
+ pCornerPoint0 = pClutData;
+
+ for (comp = 0; comp < nCompOut; comp++)
+ {
+ val0 = *pCornerPoint0++;
+
+ result = val0 << 4;
+
+ result += (val1 - val0) * interpFrac1;
+ result += (val2 - val1) * interpFrac2;
+ result += (val3 - val2) * interpFrac3;
+
+ *pOut++ = lastOut[comp] = (Uint8)(result >> 4);
+ }
+
+ return (0);
+}
+
+/* { dg-final { cleanup-tree-dump "vect" } } */
