diff options
Diffstat (limited to 'src/mesa')
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_defines.h | 2 | ||||
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_shader.cpp | 4 | ||||
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_vec4.cpp | 8 | ||||
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_vec4_generator.cpp | 44 |
4 files changed, 58 insertions, 0 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_defines.h b/src/mesa/drivers/dri/i965/brw_defines.h index a07d307764b..91d9d5225b9 100644 --- a/src/mesa/drivers/dri/i965/brw_defines.h +++ b/src/mesa/drivers/dri/i965/brw_defines.h @@ -1098,6 +1098,8 @@ enum opcode { VEC4_OPCODE_MOV_BYTES, VEC4_OPCODE_PACK_BYTES, VEC4_OPCODE_UNPACK_UNIFORM, + VEC4_OPCODE_DOUBLE_TO_FLOAT, + VEC4_OPCODE_FLOAT_TO_DOUBLE, FS_OPCODE_DDX_COARSE, FS_OPCODE_DDX_FINE, diff --git a/src/mesa/drivers/dri/i965/brw_shader.cpp b/src/mesa/drivers/dri/i965/brw_shader.cpp index 9487a3e1ee8..ec321ae1910 100644 --- a/src/mesa/drivers/dri/i965/brw_shader.cpp +++ b/src/mesa/drivers/dri/i965/brw_shader.cpp @@ -322,6 +322,10 @@ brw_instruction_name(const struct gen_device_info *devinfo, enum opcode op) return "pack_bytes"; case VEC4_OPCODE_UNPACK_UNIFORM: return "unpack_uniform"; + case VEC4_OPCODE_DOUBLE_TO_FLOAT: + return "double_to_float"; + case VEC4_OPCODE_FLOAT_TO_DOUBLE: + return "float_to_double"; case FS_OPCODE_DDX_COARSE: return "ddx_coarse"; diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp index bf36cacb0b7..3f3fd6bbcf3 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp @@ -253,6 +253,8 @@ vec4_instruction::can_do_writemask(const struct gen_device_info *devinfo) { switch (opcode) { case SHADER_OPCODE_GEN4_SCRATCH_READ: + case VEC4_OPCODE_DOUBLE_TO_FLOAT: + case VEC4_OPCODE_FLOAT_TO_DOUBLE: case VS_OPCODE_PULL_CONSTANT_LOAD: case VS_OPCODE_PULL_CONSTANT_LOAD_GEN7: case VS_OPCODE_SET_SIMD4X2_HEADER_GEN9: @@ -505,6 +507,12 @@ vec4_visitor::opt_reduce_swizzle() case BRW_OPCODE_DP2: swizzle = brw_swizzle_for_size(2); break; + + case VEC4_OPCODE_FLOAT_TO_DOUBLE: + case VEC4_OPCODE_DOUBLE_TO_FLOAT: + swizzle = brw_swizzle_for_size(4); + break; + default: swizzle = brw_swizzle_for_mask(inst->dst.writemask); break; diff --git a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp index 496766304c2..7864be1f733 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp @@ -1909,6 +1909,50 @@ generate_code(struct brw_codegen *p, break; } + case VEC4_OPCODE_DOUBLE_TO_FLOAT: { + assert(src[0].type == BRW_REGISTER_TYPE_DF); + assert(dst.type == BRW_REGISTER_TYPE_F); + + brw_set_default_access_mode(p, BRW_ALIGN_1); + + dst.hstride = BRW_HORIZONTAL_STRIDE_2; + dst.width = BRW_WIDTH_4; + src[0].vstride = BRW_VERTICAL_STRIDE_4; + src[0].width = BRW_WIDTH_4; + brw_MOV(p, dst, src[0]); + + struct brw_reg dst_as_src = dst; + dst.hstride = BRW_HORIZONTAL_STRIDE_1; + dst.width = BRW_WIDTH_8; + brw_MOV(p, dst, dst_as_src); + + brw_set_default_access_mode(p, BRW_ALIGN_16); + break; + } + + case VEC4_OPCODE_FLOAT_TO_DOUBLE: { + assert(src[0].type == BRW_REGISTER_TYPE_F); + assert(dst.type == BRW_REGISTER_TYPE_DF); + + brw_set_default_access_mode(p, BRW_ALIGN_1); + + struct brw_reg tmp = retype(dst, src[0].type); + tmp.hstride = BRW_HORIZONTAL_STRIDE_2; + tmp.width = BRW_WIDTH_4; + src[0].vstride = BRW_VERTICAL_STRIDE_4; + src[0].hstride = BRW_HORIZONTAL_STRIDE_1; + src[0].width = BRW_WIDTH_4; + brw_MOV(p, tmp, src[0]); + + tmp.vstride = BRW_VERTICAL_STRIDE_8; + tmp.hstride = BRW_HORIZONTAL_STRIDE_2; + tmp.width = BRW_WIDTH_4; + brw_MOV(p, dst, tmp); + + brw_set_default_access_mode(p, BRW_ALIGN_16); + break; + } + case VEC4_OPCODE_PACK_BYTES: { /* Is effectively: * |