swung0x48/MobileGL
1
0
Fork 0
mirror of https://github.com/MobileGL-Dev/MobileGL synced 2026-09-11 21:58:31 +09:00
Code Issues Packages Projects Releases Wiki Activity

[Test] (MG_Benchmark, MG_Util): model four more Minecraft frame patterns in the driver bench

Browse Source 
The captured traces contain per-frame patterns the bench did not exercise, and
first measurements show two of them are now the worst remaining multipliers -
which is exactly what the missing cases were hiding.

mc_pass_switch: the 26.2 snapshot switches render targets 132 times a frame and
re-declares draw buffers 198 times. Render-target churn is where a Vulkan
backend pays for render-pass breaks and where a tiler pays most on device, and
no case measured it. mc_state_toggle: Blaze3D brackets batches with blend
toggles - 46 enable/disable pairs and 28 blend-func changes per vanilla frame.
mc_tex_param: 26.2 re-sets texture parameters 612 times a frame, almost always
to the value already in place, so this measures redundant-parameter filtering.
mc_use_program: Sodium switches programs 62 times a frame with a mat4 upload on
each, roughly one switch per multi-draw.

All four live in the shared case file at the measured per-frame rates, so the
desktop harness, the on-device harness and the POST screen's Run Bench report
comparable numbers. First desktop measurements (ns/op, native / Espryt / Magma):
pass_switch 8877 / 18502 / 13896, state_toggle 1182 / 8526 / 8305,
tex_param 42 / 102 / 197, use_program 2182 / 10648 / 5096. The state-toggle
multiplier - 7x on both backends - is the largest newly exposed gap and the next
optimization target.

Unit tests 421/421; the Android JNI translation unit compiles against the
extended case set.
This commit is contained in:
BZLZHH
2026-08-06 09:39:02 -04:00
parent f2d210b12d
commit d524330032
3 changed files with 158 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
MobileGL/MG_Benchmark/Driver/DriverBenchCases.inc
+91
View File
@@ -34,6 +34,9 @@ static GLuint g_uboRing;
static GLint g_uboAlign = 256;
static size_t g_uboSlot = 256;
static GLuint g_sampler;
/* Two small offscreen targets for the 26.2-style render-pass churn case. */
static GLuint g_passFbo[2];
static GLuint g_passColor[2];
static float g_mvp[16] = {0.002f, 0, 0, 0, 0, 0.002f, 0, 0, 0, 0, -0.001f, 0, -1.f, -1.f, 0.f, 1.f};
/* Minecraft chunk vertex: pos 3f, color 4ub, uv 2f, packed light 2s -> 32 B */
@@ -162,10 +165,13 @@ static void setup_vao(GLuint vao, GLuint vbo, GLuint ibo) {
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, ibo);
}
static GLuint g_mainFbo;
static void build_resources(void) {
/* offscreen render target: 1280x720 RBO FBO, like CTS fbo surface mode */
GLuint fbo, rboColor, rboDepth;
glGenFramebuffers(1, &fbo);
g_mainFbo = fbo;
glBindFramebuffer(GL_FRAMEBUFFER, fbo);
glGenRenderbuffers(1, &rboColor);
glBindRenderbuffer(GL_RENDERBUFFER, rboColor);
@@ -257,6 +263,21 @@ static void build_resources(void) {
glBufferData(GL_UNIFORM_BUFFER, 4 * 1024 * 1024, g_scratch, GL_DYNAMIC_DRAW);
glBindBuffer(GL_UNIFORM_BUFFER, 0);
for (int i = 0; i < 2; ++i) {
glGenFramebuffers(1, &g_passFbo[i]);
glBindFramebuffer(GL_FRAMEBUFFER, g_passFbo[i]);
glGenRenderbuffers(1, &g_passColor[i]);
glBindRenderbuffer(GL_RENDERBUFFER, g_passColor[i]);
glRenderbufferStorage(GL_RENDERBUFFER, GL_RGBA8, 256, 256);
glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, g_passColor[i]);
if (glCheckFramebufferStatus(GL_FRAMEBUFFER) != GL_FRAMEBUFFER_COMPLETE) {
bench_gl_failed("pass FBO incomplete", "");
return;
}
}
/* back to the main offscreen target the harness set up */
glBindFramebuffer(GL_FRAMEBUFFER, g_mainFbo);
glGenSamplers(1, &g_sampler);
glSamplerParameteri(g_sampler, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glSamplerParameteri(g_sampler, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
@@ -516,6 +537,72 @@ static void case_mc_sampler_churn(int frame, long a, long b) {
}
/* 26.2 switches render targets constantly: 132 glBindFramebuffer and 198
* glDrawBuffers per frame. Pass switching is where a Vulkan backend pays for
* render-pass breaks, so this case is the one to watch on Magma. a = passes. */
static void case_mc_pass_switch(int frame, long a, long b) {
(void)frame; (void)b;
static const GLenum kColor0[1] = {GL_COLOR_ATTACHMENT0};
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glBindFramebuffer(GL_FRAMEBUFFER, g_passFbo[i & 1]);
glDrawBuffers(1, kColor0);
glViewport(0, 0, 256, 256);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glBindFramebuffer(GL_FRAMEBUFFER, g_mainFbo);
glViewport(0, 0, 1280, 720);
}
/* Blaze3D toggles blend around batches: 46 glEnable/glDisable pairs and 28
* glBlendFuncSeparate per vanilla frame. a = toggle pairs. */
static void case_mc_state_toggle(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glEnable(GL_BLEND);
glBlendFuncSeparate(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA, GL_ONE, GL_ZERO);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
glDisable(GL_BLEND);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
/* 26.2 re-sets texture parameters relentlessly - 612 glTexParameteri per frame,
* almost always to the value already in place. Measures redundant-param
* filtering. a = parameter writes. */
static void case_mc_tex_param(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
for (long i = 0; i < a; i += 4) {
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST_MIPMAP_LINEAR);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
/* Sodium switches programs mid-frame far more than vanilla: 62 glUseProgram and
* 60 mat4 uploads per frame. a = program switches. */
static void case_mc_use_program(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
if (i & 1) {
glUseProgram(g_progEntity);
glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
} else {
glUseProgram(g_progChunk);
glUniformMatrix4fv(g_uMvpChunk, 1, 0, g_mvp);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glUseProgram(g_progChunk);
}
/* ---- the case table both harnesses iterate --------------------------------
* a/b are the case's own knobs; opsPerFrame is what one bench frame is
* normalised by, so ns_per_op compares across renderers. The mc_* rates are
@@ -536,6 +623,10 @@ static const BenchCaseDesc kBenchCases[] = {
{"mc_tex_stream", case_mc_tex_stream, 95, 0, 95},
{"mc_uniform_lookup", case_mc_uniform_lookup, 41, 0, 41},
{"mc_sampler_churn", case_mc_sampler_churn, 306, 0, 306},
{"mc_pass_switch", case_mc_pass_switch, 132, 0, 132},
{"mc_state_toggle", case_mc_state_toggle, 46, 0, 46},
{"mc_tex_param", case_mc_tex_param, 612, 0, 612},
{"mc_use_program", case_mc_use_program, 62, 0, 62},
{"draw_tiny", case_draw_tiny, 2048, 0, 2048},
{"draw_uniform", case_draw_uniform, 2048, 0, 2048},
{"draw_multi_vao", case_draw_multi_vao, 2048, 0, 2048},