OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

amd/common: add ac_export_mrt_z() helper

Browse Source 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
This commit is contained in:
Samuel Pitoiset
2017-12-21 17:53:15 +01:00
parent 03ef264146
commit 38f9b87af2
4 changed files with 84 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
src/amd/common/ac_nir_to_llvm.c
View File

@@ -6200,67 +6200,13 @@ si_export_mrt_color(struct nir_to_llvm_context *ctx,
}
static void
si_export_mrt_z(struct nir_to_llvm_context *ctx,
LLVMValueRef depth, LLVMValueRef stencil,
LLVMValueRef samplemask)
radv_export_mrt_z(struct nir_to_llvm_context *ctx,
LLVMValueRef depth, LLVMValueRef stencil,
LLVMValueRef samplemask)
{
struct ac_export_args args;
args.enabled_channels = 0;
args.valid_mask = 1;
args.done = 1;
args.target = V_008DFC_SQ_EXP_MRTZ;
args.compr = false;
args.out[0] = LLVMGetUndef(ctx->ac.f32); /* R, depth */
args.out[1] = LLVMGetUndef(ctx->ac.f32); /* G, stencil test val[0:7], stencil op val[8:15] */
args.out[2] = LLVMGetUndef(ctx->ac.f32); /* B, sample mask */
args.out[3] = LLVMGetUndef(ctx->ac.f32); /* A, alpha to mask */
unsigned format = ac_get_spi_shader_z_format(depth != NULL,
stencil != NULL,
samplemask != NULL);
if (format == V_028710_SPI_SHADER_UINT16_ABGR) {
assert(!depth);
args.compr = 1; /* COMPR flag */
if (stencil) {
/* Stencil should be in X[23:16]. */
stencil = ac_to_integer(&ctx->ac, stencil);
stencil = LLVMBuildShl(ctx->builder, stencil,
LLVMConstInt(ctx->ac.i32, 16, 0), "");
args.out[0] = ac_to_float(&ctx->ac, stencil);
args.enabled_channels |= 0x3;
}
if (samplemask) {
/* SampleMask should be in Y[15:0]. */
args.out[1] = samplemask;
args.enabled_channels |= 0xc;
}
} else {
if (depth) {
args.out[0] = depth;
args.enabled_channels |= 0x1;
}
if (stencil) {
args.out[1] = stencil;
args.enabled_channels |= 0x2;
}
if (samplemask) {
args.out[2] = samplemask;
args.enabled_channels |= 0x4;
}
}
/* SI (except OLAND and HAINAN) has a bug that it only looks
* at the X writemask component. */
if (ctx->options->chip_class == SI &&
ctx->options->family != CHIP_OLAND &&
ctx->options->family != CHIP_HAINAN)
args.enabled_channels |= 0x1;
ac_export_mrt_z(&ctx->ac, depth, stencil, samplemask, &args);
ac_build_export(&ctx->ac, &args);
}
@@ -6308,7 +6254,7 @@ handle_fs_outputs_post(struct nir_to_llvm_context *ctx)
for (unsigned i = 0; i < index; i++)
ac_build_export(&ctx->ac, &color_args[i]);
if (depth || stencil || samplemask)
si_export_mrt_z(ctx, depth, stencil, samplemask);
radv_export_mrt_z(ctx, depth, stencil, samplemask);
else if (!index) {
si_export_mrt_color(ctx, NULL, V_008DFC_SQ_EXP_NULL, true, &color_args[0]);
ac_build_export(&ctx->ac, &color_args[0]);

72
src/amd/common/ac_shader_util.c
View File

@@ -22,7 +22,10 @@
*/
#include <assert.h>
#include <stdlib.h>
#include <string.h>
#include "ac_nir_to_llvm.h"
#include "ac_shader_util.h"
#include "sid.h"
@@ -105,3 +108,72 @@ ac_vgt_gs_mode(unsigned gs_max_vert_out, enum chip_class chip_class)
S_028A40_GS_WRITE_OPTIMIZE(1) |
S_028A40_ONCHIP(chip_class >= GFX9 ? 1 : 0);
}
void
ac_export_mrt_z(struct ac_llvm_context *ctx, LLVMValueRef depth,
LLVMValueRef stencil, LLVMValueRef samplemask,
struct ac_export_args *args)
{
unsigned mask = 0;
unsigned format = ac_get_spi_shader_z_format(depth != NULL,
stencil != NULL,
samplemask != NULL);
assert(depth || stencil || samplemask);
memset(args, 0, sizeof(*args));
args->valid_mask = 1; /* whether the EXEC mask is valid */
args->done = 1; /* DONE bit */
/* Specify the target we are exporting */
args->target = V_008DFC_SQ_EXP_MRTZ;
args->compr = 0; /* COMP flag */
args->out[0] = LLVMGetUndef(ctx->f32); /* R, depth */
args->out[1] = LLVMGetUndef(ctx->f32); /* G, stencil test val[0:7], stencil op val[8:15] */
args->out[2] = LLVMGetUndef(ctx->f32); /* B, sample mask */
args->out[3] = LLVMGetUndef(ctx->f32); /* A, alpha to mask */
if (format == V_028710_SPI_SHADER_UINT16_ABGR) {
assert(!depth);
args->compr = 1; /* COMPR flag */
if (stencil) {
/* Stencil should be in X[23:16]. */
stencil = ac_to_integer(ctx, stencil);
stencil = LLVMBuildShl(ctx->builder, stencil,
LLVMConstInt(ctx->i32, 16, 0), "");
args->out[0] = ac_to_float(ctx, stencil);
mask |= 0x3;
}
if (samplemask) {
/* SampleMask should be in Y[15:0]. */
args->out[1] = samplemask;
mask |= 0xc;
}
} else {
if (depth) {
args->out[0] = depth;
mask |= 0x1;
}
if (stencil) {
args->out[1] = stencil;
mask |= 0x2;
}
if (samplemask) {
args->out[2] = samplemask;
mask |= 0x4;
}
}
/* SI (except OLAND and HAINAN) has a bug that it only looks
* at the X writemask component. */
if (ctx->chip_class == SI &&
ctx->family != CHIP_OLAND &&
ctx->family != CHIP_HAINAN)
mask |= 0x1;
/* Specify which components to enable */
args->enabled_channels = mask;
}

6
src/amd/common/ac_shader_util.h
View File

@@ -28,6 +28,7 @@
#include <stdint.h>
#include "amd_family.h"
#include "ac_llvm_build.h"
unsigned
ac_get_spi_shader_z_format(bool writes_z, bool writes_stencil,
@@ -39,4 +40,9 @@ ac_get_cb_shader_mask(unsigned spi_shader_col_format);
uint32_t
ac_vgt_gs_mode(unsigned gs_max_vert_out, enum chip_class chip_class);
void
ac_export_mrt_z(struct ac_llvm_context *ctx, LLVMValueRef depth,
LLVMValueRef stencil, LLVMValueRef samplemask,
struct ac_export_args *args);
#endif

61
src/gallium/drivers/radeonsi/si_shader.c
View File

@@ -3425,68 +3425,9 @@ static void si_export_mrt_z(struct lp_build_tgsi_context *bld_base,
LLVMValueRef samplemask, struct si_ps_exports *exp)
{
struct si_shader_context *ctx = si_shader_context(bld_base);
struct lp_build_context *base = &bld_base->base;
struct ac_export_args args;
unsigned mask = 0;
unsigned format = ac_get_spi_shader_z_format(depth != NULL,
stencil != NULL,
samplemask != NULL);
assert(depth || stencil || samplemask);
args.valid_mask = 1; /* whether the EXEC mask is valid */
args.done = 1; /* DONE bit */
/* Specify the target we are exporting */
args.target = V_008DFC_SQ_EXP_MRTZ;
args.compr = 0; /* COMP flag */
args.out[0] = base->undef; /* R, depth */
args.out[1] = base->undef; /* G, stencil test value[0:7], stencil op value[8:15] */
args.out[2] = base->undef; /* B, sample mask */
args.out[3] = base->undef; /* A, alpha to mask */
if (format == V_028710_SPI_SHADER_UINT16_ABGR) {
assert(!depth);
args.compr = 1; /* COMPR flag */
if (stencil) {
/* Stencil should be in X[23:16]. */
stencil = ac_to_integer(&ctx->ac, stencil);
stencil = LLVMBuildShl(ctx->ac.builder, stencil,
LLVMConstInt(ctx->i32, 16, 0), "");
args.out[0] = ac_to_float(&ctx->ac, stencil);
mask |= 0x3;
}
if (samplemask) {
/* SampleMask should be in Y[15:0]. */
args.out[1] = samplemask;
mask |= 0xc;
}
} else {
if (depth) {
args.out[0] = depth;
mask |= 0x1;
}
if (stencil) {
args.out[1] = stencil;
mask |= 0x2;
}
if (samplemask) {
args.out[2] = samplemask;
mask |= 0x4;
}
}
/* SI (except OLAND and HAINAN) has a bug that it only looks
* at the X writemask component. */
if (ctx->screen->info.chip_class == SI &&
ctx->screen->info.family != CHIP_OLAND &&
ctx->screen->info.family != CHIP_HAINAN)
mask |= 0x1;
/* Specify which components to enable */
args.enabled_channels = mask;
ac_export_mrt_z(&ctx->ac, depth, stencil, samplemask, &args);
memcpy(&exp->args[exp->num++], &args, sizeof(args));
}