[Mesa-dev] [PATCH 2/2] swr: allow a single swr architecture to be builtin

[Chuck Atkins]

Part 2 of 2 (part 1 is autoconf changes, part 2 is C++ changes)

When only a single SWR architecture is being used, this allows that
architecture to be builtin rather than as a separate libswrARCH.so that
gets loaded via dlopen.  Since there are now several different code
paths for each detected CPU architecture, the log output is also
adjusted to convey where the backend is getting loaded from.

This allows SWR to be used for static mesa builds which are still
important for large HPC environments where shared libraries can impose
unacceptable application startup times as hundreds of thousands of copies
of the libs are loaded from a shared parallel filesystem.

Based on an initial implementation by Tim Rowley.

v2: Refactor repetitive preprocessor checks to reduce code duplication
v3: Formatting changes per Bruce C. Also delay screen creation until end
    to avoid leaks when failure conditions are hit.

Signed-off-by: Chuck Atkins <chuck.atkins at kitware.com>
Reviewed-by: Bruce Cherniak <bruce.cherniak at intel.com>
CC: Tim Rowley <timothy.o.rowley at intel.com>
---
 src/gallium/drivers/swr/swr_loader.cpp | 84 ++++++++++++++++++++--------------
 1 file changed, 49 insertions(+), 35 deletions(-)

diff --git a/src/gallium/drivers/swr/swr_loader.cpp b/src/gallium/drivers/swr/swr_loader.cpp
index 9d6f918e34..7f28bdb536 100644
--- a/src/gallium/drivers/swr/swr_loader.cpp
+++ b/src/gallium/drivers/swr/swr_loader.cpp
@@ -28,81 +28,95 @@
 
 #include <stdio.h>
 
+// Helper function to resolve the backend filename based on architecture
+inline void get_swr_arch_filename(const char arch[], char filename[])
+{
+#ifdef HAVE_SWR_BUILTIN
+   strcpy(filename , "builtin");
+#else
+   sprintf(filename, "%sswr%s%s", UTIL_DL_PREFIX, arch, UTIL_DL_EXT);
+#endif
+}
+
 struct pipe_screen *
 swr_create_screen(struct sw_winsys *winsys)
 {
    char filename[256] = { 0 };
-   fprintf(stderr, "SWR detected ");
-
-   util_dl_library *pLibrary = nullptr;
+   bool found = false;
+   bool is_knl = false;
+   PFNSwrGetInterface pfnSwrGetInterface = nullptr;
 
    util_cpu_detect();
 
-   bool is_knl = false;
-
-   if (!strlen(filename) &&
-       util_cpu_caps.has_avx512f && util_cpu_caps.has_avx512er) {
-#if HAVE_SWR_KNL
-      fprintf(stderr, "KNL ");
-      sprintf(filename, "%s%s%s", UTIL_DL_PREFIX, "swrKNL", UTIL_DL_EXT);
-      is_knl = true;
+   if (!found && util_cpu_caps.has_avx512f && util_cpu_caps.has_avx512er) {
+      fprintf(stderr, "SWR detected KNL instruction support ");
+#ifndef HAVE_SWR_KNL
+      fprintf(stderr, "(skipping not built).\n");
 #else
-      fprintf(stderr, "KNL (not built) ");
+      get_swr_arch_filename("KNL", filename);
+      found = true;
+      is_knl = true;
 #endif
    }
 
-   if (!strlen(filename) &&
-       util_cpu_caps.has_avx512f && util_cpu_caps.has_avx512bw) {
-#if HAVE_SWR_SKX
-      fprintf(stderr, "SKX ");
-      sprintf(filename, "%s%s%s", UTIL_DL_PREFIX, "swrSKX", UTIL_DL_EXT);
+   if (!found && util_cpu_caps.has_avx512f && util_cpu_caps.has_avx512bw) {
+      fprintf(stderr, "SWR detected SKX instruction support ");
+#ifndef HAVE_SWR_SKX
+      fprintf(stderr, "(skipping not built).\n");
 #else
-      fprintf(stderr, "SKX (not built) ");
+      get_swr_arch_filename("SKX", filename);
+      found = true;
 #endif
    }
 
-   if (!strlen(filename) && util_cpu_caps.has_avx2) {
-#if HAVE_SWR_AVX2
-      fprintf(stderr, "AVX2 ");
-      sprintf(filename, "%s%s%s", UTIL_DL_PREFIX, "swrAVX2", UTIL_DL_EXT);
+   if (!found && util_cpu_caps.has_avx2) {
+      fprintf(stderr, "SWR detected AVX2 instruction support ");
+#ifndef HAVE_SWR_AVX2
+      fprintf(stderr, "(skipping not built).\n");
 #else
-      fprintf(stderr, "AVX2 (not built) ");
+      get_swr_arch_filename("AVX2", filename);
+      found = true;
 #endif
    }
 
-   if (!strlen(filename) && util_cpu_caps.has_avx) {
-#if HAVE_SWR_AVX
-      fprintf(stderr, "AVX ");
-      sprintf(filename, "%s%s%s", UTIL_DL_PREFIX, "swrAVX", UTIL_DL_EXT);
+   if (!found && util_cpu_caps.has_avx) {
+      fprintf(stderr, "SWR detected AVX instruction support ");
+#ifndef HAVE_SWR_AVX
+      fprintf(stderr, "(skipping not built).\n");
 #else
-      fprintf(stderr, "AVX (not built) ");
+      get_swr_arch_filename("AVX", filename);
+      found = true;
 #endif
    }
 
-   if (!strlen(filename)) {
-      fprintf(stderr, "- no appropriate swr architecture library.  Aborting!\n");
+   if (!found) {
+      fprintf(stderr, "SWR could not detect a supported CPU architecture.\n");
       exit(-1);
-   } else {
-      fprintf(stderr, "\n");
    }
 
-   pLibrary = util_dl_open(filename);
+   fprintf(stderr, "(using %s).\n", filename);
 
+#ifdef HAVE_SWR_BUILTIN
+   pfnSwrGetInterface = SwrGetInterface;
+#else
+   util_dl_library *pLibrary = util_dl_open(filename);
    if (!pLibrary) {
       fprintf(stderr, "SWR library load failure: %s\n", util_dl_error());
       exit(-1);
    }
 
    util_dl_proc pApiProc = util_dl_get_proc_address(pLibrary, "SwrGetInterface");
-
    if (!pApiProc) {
       fprintf(stderr, "SWR library search failure: %s\n", util_dl_error());
       exit(-1);
    }
 
+   pfnSwrGetInterface = (PFNSwrGetInterface)pApiProc;
+#endif
+
    struct pipe_screen *screen = swr_create_screen_internal(winsys);
-   swr_screen(screen)->pfnSwrGetInterface = (PFNSwrGetInterface)pApiProc;
    swr_screen(screen)->is_knl = is_knl;
+   swr_screen(screen)->pfnSwrGetInterface = pfnSwrGetInterface;
 
    return screen;
 }
-- 
2.14.3