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

r600_shader: only load from LDS what is really used 

Use the destination write mask to determine which values are really to be
read from LDS and load only these.

Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Gert Wollny <gw.fossdev@gmail.com>
This commit is contained in:
Gert Wollny 2017-11-15 10:29:12 +01:00 committed by Dave Airlie
parent 579ec9c311
commit 76837e29e3
1 changed files with 26 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
src/gallium/drivers/r600/r600_shader.c
View File

@ -379,7 +379,7 @@ static void r600_bytecode_src(struct r600_bytecode_alu_src *bc_src,
const struct r600_shader_src *shader_src,
unsigned chan);
static int do_lds_fetch_values(struct r600_shader_ctx *ctx, unsigned temp_reg,
unsigned dst_reg);
unsigned dst_reg, unsigned mask);
static int tgsi_last_instruction(unsigned writemask)
{
@ -1026,7 +1026,7 @@ static int tgsi_declaration(struct r600_shader_ctx *ctx)
if (r)
return r;
do_lds_fetch_values(ctx, temp_reg, dreg);
do_lds_fetch_values(ctx, temp_reg, dreg, 0xf);
}
else if (d->Semantic.Name == TGSI_SEMANTIC_TESSCOORD) {
/* MOV r1.x, r0.x;
@ -1744,14 +1744,18 @@ static int r600_get_byte_address(struct r600_shader_ctx *ctx, int temp_reg,
}
static int do_lds_fetch_values(struct r600_shader_ctx *ctx, unsigned temp_reg,
unsigned dst_reg)
unsigned dst_reg, unsigned mask)
{
struct r600_bytecode_alu alu;
int r, i;
if ((ctx->bc->cf_last->ndw>>1) >= 0x60)
ctx->bc->force_add_cf = 1;
for (i = 1; i < 4; i++) {
if (!(mask & (1 << i)))
continue;
r = single_alu_op2(ctx, ALU_OP2_ADD_INT,
temp_reg, i,
temp_reg, 0,
@ -1760,6 +1764,9 @@ static int do_lds_fetch_values(struct r600_shader_ctx *ctx, unsigned temp_reg,
return r;
}
for (i = 0; i < 4; i++) {
if (! (mask & (1 << i)))
continue;
/* emit an LDS_READ_RET */
memset(&alu, 0, sizeof(alu));
alu.op = LDS_OP1_LDS_READ_RET;
@ -1775,6 +1782,8 @@ static int do_lds_fetch_values(struct r600_shader_ctx *ctx, unsigned temp_reg,
return r;
}
for (i = 0; i < 4; i++) {
if (! (mask & (1 << i)))
continue;
/* then read from LDS_OQ_A_POP */
memset(&alu, 0, sizeof(alu));
@ -1792,6 +1801,16 @@ static int do_lds_fetch_values(struct r600_shader_ctx *ctx, unsigned temp_reg,
return 0;
}
static int fetch_mask(struct tgsi_src_register *reg)
{
int mask = 0;
mask |= 1 << reg->SwizzleX;
mask |= 1 << reg->SwizzleY;
mask |= 1 << reg->SwizzleZ;
mask |= 1 << reg->SwizzleW;
return mask;
}
static int fetch_tes_input(struct r600_shader_ctx *ctx, struct tgsi_full_src_register *src, unsigned int dst_reg)
{
int r;
@ -1808,7 +1827,7 @@ static int fetch_tes_input(struct r600_shader_ctx *ctx, struct tgsi_full_src_reg
if (r)
return r;
r = do_lds_fetch_values(ctx, temp_reg, dst_reg);
r = do_lds_fetch_values(ctx, temp_reg, dst_reg, fetch_mask(&src->Register));
if (r)
return r;
return 0;
@ -1834,7 +1853,7 @@ static int fetch_tcs_input(struct r600_shader_ctx *ctx, struct tgsi_full_src_reg
if (r)
return r;
r = do_lds_fetch_values(ctx, temp_reg, dst_reg);
r = do_lds_fetch_values(ctx, temp_reg, dst_reg, fetch_mask(&src->Register));
if (r)
return r;
return 0;
@ -1856,7 +1875,7 @@ static int fetch_tcs_output(struct r600_shader_ctx *ctx, struct tgsi_full_src_re
if (r)
return r;
r = do_lds_fetch_values(ctx, temp_reg, dst_reg);
r = do_lds_fetch_values(ctx, temp_reg, dst_reg, fetch_mask(&src->Register));
if (r)
return r;
return 0;
@ -2795,7 +2814,7 @@ static int r600_tess_factor_read(struct r600_shader_ctx *ctx,
if (r)
return r;
do_lds_fetch_values(ctx, temp_reg, dreg);
do_lds_fetch_values(ctx, temp_reg, dreg, 0xf);
return 0;
}