i915: Calculate partial result to temp register first

Previously the SNE and SEQ instructions would calculate the partial
result to the destination register.  This would cause problems if the
destination register was also one of the source registers.

Fixes piglit tests glsl-fs-any, glsl-fs-struct-equal,
glsl-fs-struct-notequal, glsl-fs-vec4-operator-equal,
glsl-fs-vec4-operator-notequal.

NOTE: This is a candidate for the 7.9 and 7.10 branches.

diff --git a/src/mesa/drivers/dri/i915/i915_fragprog.c b/src/mesa/drivers/dri/i915/i915_fragprog.c
index 624f18d..8bc88a8 100644 (file)
--- a/src/mesa/drivers/dri/i915/i915_fragprog.c
+++ b/src/mesa/drivers/dri/i915/i915_fragprog.c
@@ -809,18 +809,18 @@ upload_program(struct i915_fragment_program *p)
         flags = get_result_flags(inst);
         dst = get_result_vector(p, inst);
 
-        /* dst = src1 >= src2 */
+        /* tmp = src1 >= src2 */
         i915_emit_arith(p,
                         A0_SGE,
-                        dst,
+                        tmp,
                         flags, 0,
                         src_vector(p, &inst->SrcReg[0], program),
                         src_vector(p, &inst->SrcReg[1], program),
                         0);
-        /* tmp = src1 <= src2 */
+        /* dst = src1 <= src2 */
         i915_emit_arith(p,
                         A0_SGE,
-                        tmp,
+                        dst,
                         flags, 0,
                         negate(src_vector(p, &inst->SrcReg[0], program),
                                1, 1, 1, 1),
@@ -958,18 +958,18 @@ upload_program(struct i915_fragment_program *p)
         flags = get_result_flags(inst);
         dst = get_result_vector(p, inst);
 
-        /* dst = src1 < src2 */
+        /* tmp = src1 < src2 */
         i915_emit_arith(p,
                         A0_SLT,
-                        dst,
+                        tmp,
                         flags, 0,
                         src_vector(p, &inst->SrcReg[0], program),
                         src_vector(p, &inst->SrcReg[1], program),
                         0);
-        /* tmp = src1 > src2 */
+        /* dst = src1 > src2 */
         i915_emit_arith(p,
                         A0_SLT,
-                        tmp,
+                        dst,
                         flags, 0,
                         negate(src_vector(p, &inst->SrcReg[0], program),
                                1, 1, 1, 1),