[PATCH vkd3d v3 3/6] vkd3d-shader/hlsl: Write SM4 unsigned multiplication instructions.

[Giovanni Mascellani]

Signed-off-by: Giovanni Mascellani <gmascellani at codeweavers.com>
---
v2:
 * Rename to write_sm4_binary_op_with_two_destinations().
 * Fix writemask mapping (before it always used the writemask from
   destination 1, but of course it has to use dst_idx).
v3:
 * Rebased onto master.
---
 libs/vkd3d-shader/hlsl_sm4.c | 34 +++++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/libs/vkd3d-shader/hlsl_sm4.c b/libs/vkd3d-shader/hlsl_sm4.c
index 4eebd583..3ab60c26 100644
--- a/libs/vkd3d-shader/hlsl_sm4.c
+++ b/libs/vkd3d-shader/hlsl_sm4.c
@@ -786,7 +786,7 @@ struct sm4_instruction
     {
         struct sm4_register reg;
         unsigned int writemask;
-    } dsts[1];
+    } dsts[2];
     unsigned int dst_count;
 
     struct sm4_src_register
@@ -1266,6 +1266,31 @@ static void write_sm4_binary_op(struct vkd3d_bytecode_buffer *buffer, enum vkd3d
     write_sm4_instruction(buffer, &instr);
 }
 
+static void write_sm4_binary_op_with_two_destinations(struct vkd3d_bytecode_buffer *buffer,
+        enum vkd3d_sm4_opcode opcode, const struct hlsl_ir_node *dst, unsigned dst_idx,
+        const struct hlsl_ir_node *src1, const struct hlsl_ir_node *src2)
+{
+    struct sm4_instruction instr;
+    unsigned int writemask;
+
+    memset(&instr, 0, sizeof(instr));
+    instr.opcode = opcode;
+
+    instr.dsts[1 - dst_idx].reg.type = VKD3D_SM4_RT_NULL;
+    instr.dsts[1 - dst_idx].reg.dim = VKD3D_SM4_DIMENSION_NONE;
+    instr.dsts[1 - dst_idx].reg.idx_count = 0;
+    sm4_register_from_node(&instr.dsts[dst_idx].reg, &instr.dsts[dst_idx].writemask, NULL, dst);
+    instr.dst_count = 2;
+
+    sm4_register_from_node(&instr.srcs[0].reg, &writemask, &instr.srcs[0].swizzle_type, src1);
+    instr.srcs[0].swizzle = hlsl_map_swizzle(hlsl_swizzle_from_writemask(writemask), instr.dsts[dst_idx].writemask);
+    sm4_register_from_node(&instr.srcs[1].reg, &writemask, &instr.srcs[1].swizzle_type, src2);
+    instr.srcs[1].swizzle = hlsl_map_swizzle(hlsl_swizzle_from_writemask(writemask), instr.dsts[dst_idx].writemask);
+    instr.src_count = 2;
+
+    write_sm4_instruction(buffer, &instr);
+}
+
 static void write_sm4_constant(struct hlsl_ctx *ctx,
         struct vkd3d_bytecode_buffer *buffer, const struct hlsl_ir_constant *constant)
 {
@@ -1578,6 +1603,13 @@ static void write_sm4_expr(struct hlsl_ctx *ctx,
                     write_sm4_binary_op(buffer, VKD3D_SM4_OP_UMIN, &expr->node, arg1, arg2);
                     break;
 
+                case HLSL_OP2_MUL:
+                    /* Using IMUL instead of UMUL because we're taking
+                     * the low bits, and the native compiler generates
+                     * IMUL. */
+                    write_sm4_binary_op_with_two_destinations(buffer, VKD3D_SM4_OP_IMUL, &expr->node, 1, arg1, arg2);
+                    break;
+
                 default:
                     hlsl_fixme(ctx, &expr->node.loc, "SM4 uint \"%s\" expression.\n", debug_hlsl_expr_op(expr->op));
                     break;
-- 
2.34.1