For now under debug flag, since only suitable for debugging/testing.
---
src/gallium/drivers/freedreno/freedreno_screen.c | 5 +++-
src/gallium/drivers/freedreno/freedreno_util.h | 1 +
.../drivers/freedreno/ir3/ir3_compiler_nir.c | 15 ++++++++++-
src/gallium/drivers/freedreno/ir3/ir3_shader.c | 30 +++++++++++++++++++---
src/gallium/drivers/freedreno/ir3/ir3_shader.h | 3 +++
5 files changed, 48 insertions(+), 6 deletions(-)
diff --git a/src/gallium/drivers/freedreno/freedreno_screen.c
b/src/gallium/drivers/freedreno/freedreno_screen.c
index b64f78c..30def8e 100644
--- a/src/gallium/drivers/freedreno/freedreno_screen.c
+++ b/src/gallium/drivers/freedreno/freedreno_screen.c
@@ -71,6 +71,7 @@ static const struct debug_named_value debug_options[] = {
{"glsl120", FD_DBG_GLSL120,"Temporary flag to force GLSL 1.20
(rather than 1.30) on a3xx+"},
{"shaderdb", FD_DBG_SHADERDB, "Enable shaderdb output"},
{"flush", FD_DBG_FLUSH, "Force flush after every draw"},
+ {"nir", FD_DBG_NIR, "Prefer NIR as native IR"},
DEBUG_NAMED_VALUE_END
};
@@ -398,7 +399,7 @@ fd_screen_get_shader_param(struct pipe_screen *pscreen,
unsigned shader,
case PIPE_SHADER_CAP_TGSI_DROUND_SUPPORTED:
case PIPE_SHADER_CAP_TGSI_DFRACEXP_DLDEXP_SUPPORTED:
case PIPE_SHADER_CAP_TGSI_FMA_SUPPORTED:
- case PIPE_SHADER_CAP_TGSI_ANY_INOUT_DECL_RANGE:
+ case PIPE_SHADER_CAP_TGSI_ANY_INOUT_DECL_RANGE:
return 0;
case PIPE_SHADER_CAP_TGSI_SQRT_SUPPORTED:
return 1;
@@ -410,6 +411,8 @@ fd_screen_get_shader_param(struct pipe_screen *pscreen,
unsigned shader,
case PIPE_SHADER_CAP_MAX_SAMPLER_VIEWS:
return 16;
case PIPE_SHADER_CAP_PREFERRED_IR:
+ if ((fd_mesa_debug & FD_DBG_NIR) && is_ir3(screen))
+ return PIPE_SHADER_IR_NIR;
return PIPE_SHADER_IR_TGSI;
}
debug_printf("unknown shader param %d\n", param);
diff --git a/src/gallium/drivers/freedreno/freedreno_util.h
b/src/gallium/drivers/freedreno/freedreno_util.h
index 0d2418e..56d3235 100644
--- a/src/gallium/drivers/freedreno/freedreno_util.h
+++ b/src/gallium/drivers/freedreno/freedreno_util.h
@@ -73,6 +73,7 @@ enum adreno_stencil_op fd_stencil_op(unsigned op);
#define FD_DBG_GLSL120 0x0400
#define FD_DBG_SHADERDB 0x0800
#define FD_DBG_FLUSH 0x1000
+#define FD_DBG_NIR 0x2000
extern int fd_mesa_debug;
extern bool fd_binning_enabled;
diff --git a/src/gallium/drivers/freedreno/ir3/ir3_compiler_nir.c
b/src/gallium/drivers/freedreno/ir3/ir3_compiler_nir.c
index b4e5483..5a53e32 100644
--- a/src/gallium/drivers/freedreno/ir3/ir3_compiler_nir.c
+++ b/src/gallium/drivers/freedreno/ir3/ir3_compiler_nir.c
@@ -164,7 +164,14 @@ to_nir(struct ir3_compile *ctx, struct ir3_shader_variant
*so)
tex_options.lower_txp = (1 << GLSL_SAMPLER_DIM_3D);
}
- struct nir_shader *s = tgsi_to_nir(so->shader->tokens, &options);
+ struct nir_shader *s;
+
+ if (so->shader->nir) {
+ // XXX need nir_clone() here..
+ s = so->shader->nir;
+ } else {
+ s = tgsi_to_nir(so->shader->tokens, &options);
+ }
if (fd_mesa_debug & FD_DBG_OPTMSGS) {
debug_printf("----------------------\n");
@@ -292,6 +299,12 @@ compile_error(struct ir3_compile *ctx, const char *format,
...)
static void
compile_free(struct ir3_compile *ctx)
{
+ /* TODO .. probably need a ralloc_free(ctx->s) here, at least
+ * for the tgsi_to_nir case.. right now in the case we get
+ * NIR directly, we want to skip this since the nir_shader isn't
+ * getting cloned.. and/or if it was we might be wanting to
+ * free it in ir3_shader_destroy()??
+ */
ralloc_free(ctx);
}
diff --git a/src/gallium/drivers/freedreno/ir3/ir3_shader.c
b/src/gallium/drivers/freedreno/ir3/ir3_shader.c
index 7b56533..0cbf8fe 100644
--- a/src/gallium/drivers/freedreno/ir3/ir3_shader.c
+++ b/src/gallium/drivers/freedreno/ir3/ir3_shader.c
@@ -39,6 +39,7 @@
#include "ir3_shader.h"
#include "ir3_compiler.h"
+#include "ir3_nir.h"
static void
@@ -188,9 +189,15 @@ create_variant(struct ir3_shader *shader, struct
ir3_shader_key key)
v->type = shader->type;
if (fd_mesa_debug & FD_DBG_DISASM) {
- DBG("dump tgsi: type=%d, k={bp=%u,cts=%u,hp=%u}", shader->type,
- key.binning_pass, key.color_two_side,
key.half_precision);
- tgsi_dump(shader->tokens, 0);
+ if (shader->nir) {
+ DBG("dump nir: type=%d, k={bp=%u,cts=%u,hp=%u}",
shader->type,
+ key.binning_pass, key.color_two_side,
key.half_precision);
+ nir_print_shader(shader->nir, stderr);
+ } else {
+ DBG("dump tgsi: type=%d, k={bp=%u,cts=%u,hp=%u}",
shader->type,
+ key.binning_pass, key.color_two_side,
key.half_precision);
+ tgsi_dump(shader->tokens, 0);
+ }
}
ret = ir3_compile_shader_nir(shader->compiler, v);
@@ -267,7 +274,9 @@ ir3_shader_destroy(struct ir3_shader *shader)
v = v->next;
delete_variant(t);
}
+
free((void *)shader->tokens);
+ /* XXX ralloc_free(shader->nir); */
free(shader);
}
@@ -281,7 +290,20 @@ ir3_shader_create(struct pipe_context *pctx,
shader->id = ++shader->compiler->shader_count;
shader->pctx = pctx;
shader->type = type;
- shader->tokens = tgsi_dup_tokens(cso->tokens);
+ if (cso->ir == PIPE_SHADER_IR_NIR) {
+ /* TODO might need nir_clone() here.. Depends a bit on how we
+ * define the lifecycle of cso->nir. If we could assume that it
+ * always sticks around until the cso is destroyed, then we'd
+ * only need to clone in to_nir() (for the variant specific
+ * lowering), rather than both here and to_nir(). This is a bit
+ * different from the lifetime of cso->tokens which sometimes
+ * but not always goes away after the
pipe->pipe_create_xyz_state()
+ * call (which is unfortunate, and maybe worth fixing).
+ */
+ shader->nir = cso->nir;
+ } else {
+ shader->tokens = tgsi_dup_tokens(cso->tokens);
+ }
shader->stream_output = cso->stream_output;
if (fd_mesa_debug & FD_DBG_SHADERDB) {
/* if shader-db run, create a standard variant immediately
diff --git a/src/gallium/drivers/freedreno/ir3/ir3_shader.h
b/src/gallium/drivers/freedreno/ir3/ir3_shader.h
index 7e2c27d..9ef3277 100644
--- a/src/gallium/drivers/freedreno/ir3/ir3_shader.h
+++ b/src/gallium/drivers/freedreno/ir3/ir3_shader.h
@@ -220,6 +220,8 @@ struct ir3_shader_variant {
struct ir3_shader *shader;
};
+typedef struct nir_shader nir_shader;
+
struct ir3_shader {
enum shader_t type;
@@ -230,6 +232,7 @@ struct ir3_shader {
struct ir3_compiler *compiler;
struct pipe_context *pctx;
+ nir_shader *nir;
const struct tgsi_token *tokens;
struct pipe_stream_output_info stream_output;
--
2.5.0
