vc4: In a loop break/continue, jump if everyone has taken the path.

This should be a win for most loops, which tend to have uniform control
flow.

More importantly, it exposes important information to live variables: that
the break/continue here means that our jump target may have access to
values that were live on our input.  Previously, we were just setting the
exec mask and letting control flow fall through, so an intervening def
between the break and the end of the loop would appear to live variables
as if it screened off the variable, when it didn't actually.

Fixes a regression in glsl-vs-loop-redundant-condition.shader_test when a
perturbing of register allocation caused a live variable to get stomped.

Cc: 13.0 <[email protected]>

1 files changed, 17 insertions, 10 deletions

diff --git a/src/gallium/drivers/vc4/vc4_program.c b/src/gallium/drivers/vc4/vc4_program.c
index 66fd902b695..a7c92d577b8 100644
--- a/src/gallium/drivers/vc4/vc4_program.c
+++ b/src/gallium/drivers/vc4/vc4_program.c
@@ -1957,22 +1957,29 @@ ntq_emit_if(struct vc4_compile *c, nir_if *if_stmt)
 static void
 ntq_emit_jump(struct vc4_compile *c, nir_jump_instr *jump)
 {
+        struct qblock *jump_block;
         switch (jump->type) {
         case nir_jump_break:
-                qir_SF(c, c->execute);
-                qir_MOV_cond(c, QPU_COND_ZS, c->execute,
-                             qir_uniform_ui(c, c->loop_break_block->index));
+                jump_block = c->loop_break_block;
                 break;
-
         case nir_jump_continue:
-                qir_SF(c, c->execute);
-                qir_MOV_cond(c, QPU_COND_ZS, c->execute,
-                             qir_uniform_ui(c, c->loop_cont_block->index));
+                jump_block = c->loop_cont_block;
                 break;
-
-        case nir_jump_return:
-                unreachable("All returns shouold be lowered\n");
+        default:
+                unreachable("Unsupported jump type\n");
         }
+
+        qir_SF(c, c->execute);
+        qir_MOV_cond(c, QPU_COND_ZS, c->execute,
+                     qir_uniform_ui(c, jump_block->index));
+
+        /* Jump to the destination block if everyone has taken the jump. */
+        qir_SF(c, qir_SUB(c, c->execute, qir_uniform_ui(c, jump_block->index)));
+        qir_BRANCH(c, QPU_COND_BRANCH_ALL_ZS);
+        struct qblock *new_block = qir_new_block(c);
+        qir_link_blocks(c->cur_block, jump_block);
+        qir_link_blocks(c->cur_block, new_block);
+        qir_set_emit_block(c, new_block);
 }
 
 static void