summaryrefslogtreecommitdiffstats
path: root/src/broadcom/compiler
diff options
context:
space:
mode:
authorIan Romanick <[email protected]>2018-08-18 16:42:04 -0700
committerIan Romanick <[email protected]>2019-05-06 22:52:29 -0700
commitd41cdef2a591930ad848b27f936aafcafc93b308 (patch)
treec1527e05de52fc8c05b571c3dcfac7defb5c2d73 /src/broadcom/compiler
parent158370ed2a012574bcc18e98075712da04fe22e8 (diff)
nir: Use the flrp lowering pass instead of nir_opt_algebraic
I tried to be very careful while updating all the various drivers, but I don't have any of that hardware for testing. :( i965 is the only platform that sets always_precise = true, and it is only set true for fragment shaders. Gen4 and Gen5 both set lower_flrp32 only for vertex shaders. For fragment shaders, nir_op_flrp is lowered during code generation as a(1-c)+bc. On all other platforms 64-bit nir_op_flrp and on Gen11 32-bit nir_op_flrp are lowered using the old nir_opt_algebraic method. No changes on any other Intel platforms. v2: Add panfrost changes. Iron Lake and GM45 had similar results. (Iron Lake shown) total cycles in shared programs: 188647754 -> 188647748 (<.01%) cycles in affected programs: 5096 -> 5090 (-0.12%) helped: 3 HURT: 0 helped stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2 helped stats (rel) min: 0.12% max: 0.12% x̄: 0.12% x̃: 0.12% Reviewed-by: Matt Turner <[email protected]>
Diffstat (limited to 'src/broadcom/compiler')
-rw-r--r--src/broadcom/compiler/nir_to_vir.c23
1 files changed, 23 insertions, 0 deletions
diff --git a/src/broadcom/compiler/nir_to_vir.c b/src/broadcom/compiler/nir_to_vir.c
index 1556dbee45e..3e82f61d6ea 100644
--- a/src/broadcom/compiler/nir_to_vir.c
+++ b/src/broadcom/compiler/nir_to_vir.c
@@ -1301,6 +1301,10 @@ void
v3d_optimize_nir(struct nir_shader *s)
{
bool progress;
+ unsigned lower_flrp =
+ (s->options->lower_flrp16 ? 16 : 0) |
+ (s->options->lower_flrp32 ? 32 : 0) |
+ (s->options->lower_flrp64 ? 64 : 0);
do {
progress = false;
@@ -1316,6 +1320,25 @@ v3d_optimize_nir(struct nir_shader *s)
NIR_PASS(progress, s, nir_opt_peephole_select, 8, true, true);
NIR_PASS(progress, s, nir_opt_algebraic);
NIR_PASS(progress, s, nir_opt_constant_folding);
+
+ if (lower_flrp != 0) {
+ bool lower_flrp_progress;
+
+ NIR_PASS(lower_flrp_progress, s, nir_lower_flrp,
+ lower_flrp,
+ false /* always_precise */,
+ s->options->lower_ffma);
+ if (lower_flrp_progress) {
+ NIR_PASS(progress, s, nir_opt_constant_folding);
+ progress = true;
+ }
+
+ /* Nothing should rematerialize any flrps, so we only
+ * need to do this lowering once.
+ */
+ lower_flrp = 0;
+ }
+
NIR_PASS(progress, s, nir_opt_undef);
} while (progress);