radeonsi/nir: don't lower fma, instead, fuse fma
We want fma. This decreases compile times by 4% for Borderlands 2. 48505 shaders in 30515 tests Totals: SGPRS: 2206584 -> 2204784 (-0.08 %) VGPRS: 1647892 -> 1648964 (0.07 %) Spilled SGPRs: 6256 -> 6078 (-2.85 %) Spilled VGPRs: 72 -> 72 (0.00 %) Private memory VGPRs: 2176 -> 2176 (0.00 %) Scratch size: 2240 -> 2240 (0.00 %) dwords per thread Code Size: 49680804 -> 49837988 (0.32 %) bytes LDS: 74 -> 74 (0.00 %) blocks Max Waves: 371387 -> 371352 (-0.01 %) Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
This commit is contained in:
parent
dec34e880d
commit
bda3ec5d55
|
@ -511,7 +511,7 @@ static const struct nir_shader_compiler_options nir_options = {
|
|||
.lower_bitfield_insert_to_bitfield_select = true,
|
||||
.lower_bitfield_extract = true,
|
||||
.lower_sub = true,
|
||||
.lower_ffma = true,
|
||||
.fuse_ffma = true,
|
||||
.lower_fmod = true,
|
||||
.lower_pack_snorm_4x8 = true,
|
||||
.lower_pack_unorm_4x8 = true,
|
||||
|
|
Loading…
Reference in New Issue