KonstantinSeurer
/
mesa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

nir: Fix output swizzle in get_mul_for_src 

When we compute the output swizzle we want to consider the number of
components in the add operation. So far we were using the writemask
of the multiplication for this instead, which is not correct.

Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
This commit is contained in:
Iago Toral Quiroga 2015-05-28 09:06:33 +02:00
parent 09d6243aed
commit 2231cf0ba3
1 changed files with 9 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/glsl/nir/nir_opt_peephole_ffma.c
View File

@ -73,7 +73,8 @@ are_all_uses_fadd(nir_ssa_def *def)
}
static nir_alu_instr *
get_mul_for_src(nir_alu_src *src, uint8_t swizzle[4], bool *negate, bool *abs)
get_mul_for_src(nir_alu_src *src, int num_components,
uint8_t swizzle[4], bool *negate, bool *abs)
{
assert(src->src.is_ssa && !src->abs && !src->negate);
@ -85,16 +86,16 @@ get_mul_for_src(nir_alu_src *src, uint8_t swizzle[4], bool *negate, bool *abs)
switch (alu->op) {
case nir_op_imov:
case nir_op_fmov:
alu = get_mul_for_src(&alu->src[0], swizzle, negate, abs);
alu = get_mul_for_src(&alu->src[0], num_components, swizzle, negate, abs);
break;
case nir_op_fneg:
alu = get_mul_for_src(&alu->src[0], swizzle, negate, abs);
alu = get_mul_for_src(&alu->src[0], num_components, swizzle, negate, abs);
*negate = !*negate;
break;
case nir_op_fabs:
alu = get_mul_for_src(&alu->src[0], swizzle, negate, abs);
alu = get_mul_for_src(&alu->src[0], num_components, swizzle, negate, abs);
*negate = false;
*abs = true;
break;
@ -115,12 +116,8 @@ get_mul_for_src(nir_alu_src *src, uint8_t swizzle[4], bool *negate, bool *abs)
if (!alu)
return NULL;
for (unsigned i = 0; i < 4; i++) {
if (!(alu->dest.write_mask & (1 << i)))
break;
for (unsigned i = 0; i < num_components; i++)
swizzle[i] = swizzle[src->swizzle[i]];
}
return alu;
}
@ -160,7 +157,9 @@ nir_opt_peephole_ffma_block(nir_block *block, void *void_state)
negate = false;
abs = false;
mul = get_mul_for_src(&add->src[add_mul_src], swizzle, &negate, &abs);
mul = get_mul_for_src(&add->src[add_mul_src],
add->dest.dest.ssa.num_components,
swizzle, &negate, &abs);
if (mul != NULL)
break;