VEC4_OPCODE_FLOAT_TO_DOUBLE,
VEC4_OPCODE_PICK_LOW_32BIT,
VEC4_OPCODE_PICK_HIGH_32BIT,
+ VEC4_OPCODE_SET_LOW_32BIT,
+ VEC4_OPCODE_SET_HIGH_32BIT,
FS_OPCODE_DDX_COARSE,
FS_OPCODE_DDX_FINE,
return "pick_low_32bit";
case VEC4_OPCODE_PICK_HIGH_32BIT:
return "pick_high_32bit";
+ case VEC4_OPCODE_SET_LOW_32BIT:
+ return "set_low_32bit";
+ case VEC4_OPCODE_SET_HIGH_32BIT:
+ return "set_high_32bit";
case FS_OPCODE_DDX_COARSE:
return "ddx_coarse";
case VEC4_OPCODE_FLOAT_TO_DOUBLE:
case VEC4_OPCODE_PICK_LOW_32BIT:
case VEC4_OPCODE_PICK_HIGH_32BIT:
+ case VEC4_OPCODE_SET_LOW_32BIT:
+ case VEC4_OPCODE_SET_HIGH_32BIT:
case VS_OPCODE_PULL_CONSTANT_LOAD:
case VS_OPCODE_PULL_CONSTANT_LOAD_GEN7:
case VS_OPCODE_SET_SIMD4X2_HEADER_GEN9:
case VEC4_OPCODE_DOUBLE_TO_FLOAT:
case VEC4_OPCODE_PICK_LOW_32BIT:
case VEC4_OPCODE_PICK_HIGH_32BIT:
+ case VEC4_OPCODE_SET_LOW_32BIT:
+ case VEC4_OPCODE_SET_HIGH_32BIT:
swizzle = brw_swizzle_for_size(4);
break;
break;
}
+ case VEC4_OPCODE_SET_LOW_32BIT:
+ case VEC4_OPCODE_SET_HIGH_32BIT: {
+ /* Reads consecutive 32-bit elements from src[0] and writes
+ * them to the low/high 32-bit of each 64-bit element in dst.
+ */
+ assert(type_sz(src[0].type) == 4);
+ assert(type_sz(dst.type) == 8);
+
+ brw_set_default_access_mode(p, BRW_ALIGN_1);
+
+ dst = retype(dst, BRW_REGISTER_TYPE_UD);
+ if (inst->opcode == VEC4_OPCODE_SET_HIGH_32BIT)
+ dst = suboffset(dst, 1);
+ dst.hstride = BRW_HORIZONTAL_STRIDE_2;
+
+ src[0] = retype(src[0], BRW_REGISTER_TYPE_UD);
+ src[0].vstride = BRW_VERTICAL_STRIDE_4;
+ src[0].width = BRW_WIDTH_4;
+ src[0].hstride = BRW_HORIZONTAL_STRIDE_1;
+ brw_MOV(p, dst, src[0]);
+
+ brw_set_default_access_mode(p, BRW_ALIGN_16);
+ break;
+ }
+
case VEC4_OPCODE_PACK_BYTES: {
/* Is effectively:
*