summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorIago Toral Quiroga <[email protected]>2016-08-26 10:01:59 +0200
committerIago Toral Quiroga <[email protected]>2016-08-29 08:09:09 +0200
commit9c9f45b82410646d2f7a8576d03de9916118bf07 (patch)
treeca401e11d8192e2500ed16cdd48e2abfdf5d0355
parent22cec6dc5e5a3060bc87f4a92871b4f6eef04632 (diff)
i965/vec4: remove the generator hack for dual instanced GS
This hack was introduced in commit 03ac2c7223f7645e3: i965/gs: Fix up gl_PointSize input swizzling for DUAL_INSTANCED gs Specifically to fixup the code we emitted to deal with gl_PointSize inputs in dual instance mode, where we were emitting a MOV to copy the point size from .w (where the hardware delivers it) to .x (because code will expect this to be a float). This meant that we were emitting a MOV to an ATTR destination that could have a width of 4 (in dual instanced mode) so it was necessary to fix the execution size and regioning of the instruction. Fortunately, Ken fixed this in 67c5d00273ca2: i965/vec4/gs: Stop munging the ATTR containing gl_PointSize. by using a WWWW swizzle instead of a MOV, and as the commit log in that patch states, we no longer emit instructions with ATTR destinations, so that makes the fixup code in the generator unnecessary. Reviewed-by: Francisco Jerez <[email protected]>
-rw-r--r--src/mesa/drivers/dri/i965/brw_vec4_generator.cpp31
1 files changed, 0 insertions, 31 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
index 399b2c627d7..b428d3a92e3 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
@@ -1503,34 +1503,6 @@ generate_code(struct brw_codegen *p,
assert(inst->mlen <= BRW_MAX_MSG_LENGTH);
unsigned pre_emit_nr_insn = p->nr_insn;
- bool fix_exec_size = false;
-
- if (dst.width == BRW_WIDTH_4) {
- /* This happens in attribute fixups for "dual instanced" geometry
- * shaders, since they use attributes that are vec4's. Since the exec
- * width is only 4, it's essential that the caller set
- * force_writemask_all in order to make sure the instruction is executed
- * regardless of which channels are enabled.
- */
- assert(inst->force_writemask_all);
-
- /* Fix up any <8;8,1> or <0;4,1> source registers to <4;4,1> to satisfy
- * the following register region restrictions (from Graphics BSpec:
- * 3D-Media-GPGPU Engine > EU Overview > Registers and Register Regions
- * > Register Region Restrictions)
- *
- * 1. ExecSize must be greater than or equal to Width.
- *
- * 2. If ExecSize = Width and HorzStride != 0, VertStride must be set
- * to Width * HorzStride."
- */
- for (int i = 0; i < 3; i++) {
- if (src[i].file == BRW_GENERAL_REGISTER_FILE)
- src[i] = stride(src[i], 4, 4, 1);
- }
- brw_set_default_exec_size(p, BRW_EXECUTE_4);
- fix_exec_size = true;
- }
switch (inst->opcode) {
case VEC4_OPCODE_UNPACK_UNIFORM:
@@ -2034,9 +2006,6 @@ generate_code(struct brw_codegen *p,
unreachable("Unsupported opcode");
}
- if (fix_exec_size)
- brw_set_default_exec_size(p, BRW_EXECUTE_8);
-
if (inst->opcode == VEC4_OPCODE_PACK_BYTES) {
/* Handled dependency hints in the generator. */