gallivm: Make it possible to disable some optimization shortcuts in release builds

For testing it is of interest that all tests of dEQP pass, e.g. to test
virglrenderer on a host only providing software rendering like in a CI.
Hence make it possible to disable certain optimizations that make tests fail.

While we are there also add some documentation to the flags to make it clear
that this is opt-out.

Setting the environment variable "GALLIVM_PERF=no_filter_hacks" can be used to make
the following tests pass in release mode:

  dEQP-GLES2.functional.texture.mipmap.2d.affine.*_linear_*
  dEQP-GLES2.functional.texture.mipmap.cube.generate.*
  dEQP-GLES2.functional.texture.vertex.2d.filtering.*_mipmap_linear_*
  dEQP-GLES2.functional.texture.vertex.2d.wrap.*

Related:
  https://bugs.freedesktop.org/show_bug.cgi?id=94957

v2: rename optimization disabling flag to 'safemath' and also move the
    nopt flag to the perf flags.

v3: rename flag "safemath" to "no_filter_hacks" since safemath is usually
    associated with floating point operations (Roland)

Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>

4 files changed, 32 insertions, 21 deletions

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_debug.h b/src/gallium/auxiliary/gallivm/lp_bld_debug.h
index f96a1afa7aa..eeef0d6ba61 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_debug.h
+++ b/src/gallium/auxiliary/gallivm/lp_bld_debug.h
@@ -39,20 +39,22 @@
 #define GALLIVM_DEBUG_TGSI          (1 << 0)
 #define GALLIVM_DEBUG_IR            (1 << 1)
 #define GALLIVM_DEBUG_ASM           (1 << 2)
-#define GALLIVM_DEBUG_NO_OPT        (1 << 3)
-#define GALLIVM_DEBUG_PERF          (1 << 4)
-#define GALLIVM_DEBUG_NO_BRILINEAR  (1 << 5)
-#define GALLIVM_DEBUG_NO_RHO_APPROX (1 << 6)
-#define GALLIVM_DEBUG_NO_QUAD_LOD   (1 << 7)
-#define GALLIVM_DEBUG_GC            (1 << 8)
-#define GALLIVM_DEBUG_DUMP_BC       (1 << 9)
+#define GALLIVM_DEBUG_PERF          (1 << 3)
+#define GALLIVM_DEBUG_GC            (1 << 4)
+#define GALLIVM_DEBUG_DUMP_BC       (1 << 5)
 
+#define GALLIVM_PERF_NO_BRILINEAR  (1 << 0)
+#define GALLIVM_PERF_NO_RHO_APPROX (1 << 1)
+#define GALLIVM_PERF_NO_QUAD_LOD   (1 << 2)
+#define GALLIVM_PERF_NO_OPT        (1 << 3)
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
 
+extern unsigned gallivm_perf;
+
 #ifdef DEBUG
 extern unsigned gallivm_debug;
 #else
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_init.c b/src/gallium/auxiliary/gallivm/lp_bld_init.c
index 1f0a01cde67..e8bca5bc3af 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_init.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_init.c
@@ -59,6 +59,17 @@ static const bool use_mcjit = USE_MCJIT;
 static bool use_mcjit = FALSE;
 #endif
 
+unsigned gallivm_perf = 0;
+
+static const struct debug_named_value lp_bld_perf_flags[] = {
+   { "no_brilinear", GALLIVM_PERF_NO_BRILINEAR, "disable brilinear optimization" },
+   { "no_rho_approx", GALLIVM_PERF_NO_RHO_APPROX, "disable rho_approx optimization" },
+   { "no_quad_lod", GALLIVM_PERF_NO_QUAD_LOD, "disable quad_lod optimization" },
+   { "nopt",   GALLIVM_PERF_NO_OPT, "disable optimization passes to speed up shader compilation" },
+   { "no_filter_hacks", GALLIVM_PERF_NO_BRILINEAR | GALLIVM_PERF_NO_RHO_APPROX |
+     GALLIVM_PERF_NO_QUAD_LOD, "disable filter optimization hacks" },
+   DEBUG_NAMED_VALUE_END
+};
 
 #ifdef DEBUG
 unsigned gallivm_debug = 0;
@@ -67,11 +78,7 @@ static const struct debug_named_value lp_bld_debug_flags[] = {
    { "tgsi",   GALLIVM_DEBUG_TGSI, NULL },
    { "ir",     GALLIVM_DEBUG_IR, NULL },
    { "asm",    GALLIVM_DEBUG_ASM, NULL },
-   { "nopt",   GALLIVM_DEBUG_NO_OPT, NULL },
    { "perf",   GALLIVM_DEBUG_PERF, NULL },
-   { "no_brilinear", GALLIVM_DEBUG_NO_BRILINEAR, NULL },
-   { "no_rho_approx", GALLIVM_DEBUG_NO_RHO_APPROX, NULL },
-   { "no_quad_lod", GALLIVM_DEBUG_NO_QUAD_LOD, NULL },
    { "gc",     GALLIVM_DEBUG_GC, NULL },
    { "dumpbc", GALLIVM_DEBUG_DUMP_BC, NULL },
    DEBUG_NAMED_VALUE_END
@@ -136,7 +143,7 @@ create_pass_manager(struct gallivm_state *gallivm)
       free(td_str);
    }
 
-   if ((gallivm_debug & GALLIVM_DEBUG_NO_OPT) == 0) {
+   if ((gallivm_perf & GALLIVM_PERF_NO_OPT) == 0) {
       /*
        * TODO: Evaluate passes some more - keeping in mind
        * both quality of generated code and compile times.
@@ -240,7 +247,7 @@ init_gallivm_engine(struct gallivm_state *gallivm)
       char *error = NULL;
       int ret;
 
-      if (gallivm_debug & GALLIVM_DEBUG_NO_OPT) {
+      if (gallivm_perf & GALLIVM_PERF_NO_OPT) {
          optlevel = None;
       }
       else {
@@ -420,6 +427,8 @@ lp_build_init(void)
    gallivm_debug = debug_get_option_gallivm_debug();
 #endif
 
+   gallivm_perf = debug_get_flags_option("GALLIVM_PERF", lp_bld_perf_flags, 0 );
+
    lp_set_target_options();
 
    util_cpu_detect();
@@ -589,10 +598,10 @@ gallivm_compile_module(struct gallivm_state *gallivm)
       LLVMWriteBitcodeToFile(gallivm->module, filename);
       debug_printf("%s written\n", filename);
       debug_printf("Invoke as \"opt %s %s | llc -O%d %s%s\"\n",
-                   gallivm_debug & GALLIVM_DEBUG_NO_OPT ? "-mem2reg" :
+                   gallivm_debug & GALLIVM_PERF_NO_OPT ? "-mem2reg" :
                    "-sroa -early-cse -simplifycfg -reassociate "
                    "-mem2reg -constprop -instcombine -gvn",
-                   filename, gallivm_debug & GALLIVM_DEBUG_NO_OPT ? 0 : 2,
+                   filename, gallivm_debug & GALLIVM_PERF_NO_OPT ? 0 : 2,
                    (HAVE_LLVM >= 0x0305) ? "[-mcpu=<-mcpu option>] " : "",
                    "[-mattr=<-mattr option(s)>]");
    }
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c b/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
index 8f760f59fed..018cca8f9df 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
@@ -2825,13 +2825,13 @@ lp_build_sample_soa_code(struct gallivm_state *gallivm,
    bld.format_desc = util_format_description(static_texture_state->format);
    bld.dims = dims;
 
-   if (gallivm_debug & GALLIVM_DEBUG_NO_QUAD_LOD || op_is_lodq) {
+   if (gallivm_perf & GALLIVM_PERF_NO_QUAD_LOD || op_is_lodq) {
       bld.no_quad_lod = TRUE;
    }
-   if (gallivm_debug & GALLIVM_DEBUG_NO_RHO_APPROX || op_is_lodq) {
+   if (gallivm_perf & GALLIVM_PERF_NO_RHO_APPROX || op_is_lodq) {
       bld.no_rho_approx = TRUE;
    }
-   if (gallivm_debug & GALLIVM_DEBUG_NO_BRILINEAR || op_is_lodq) {
+   if (gallivm_perf & GALLIVM_PERF_NO_BRILINEAR || op_is_lodq) {
       bld.no_brilinear = TRUE;
    }
 
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_tgsi_soa.c b/src/gallium/auxiliary/gallivm/lp_bld_tgsi_soa.c
index 79ece639e35..5fecad4ea67 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_tgsi_soa.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_tgsi_soa.c
@@ -2037,7 +2037,7 @@ lp_build_lod_property(
       lod_property = LP_SAMPLER_LOD_SCALAR;
    }
    else if (bld_base->info->processor == PIPE_SHADER_FRAGMENT) {
-      if (gallivm_debug & GALLIVM_DEBUG_NO_QUAD_LOD) {
+      if (gallivm_perf & GALLIVM_PERF_NO_QUAD_LOD) {
          lod_property = LP_SAMPLER_LOD_PER_ELEMENT;
       }
       else {
@@ -2225,7 +2225,7 @@ emit_tex( struct lp_build_tgsi_soa_context *bld,
        * cases exist in practice.
        */
       if (bld->bld_base.info->processor == PIPE_SHADER_FRAGMENT) {
-         if (gallivm_debug & GALLIVM_DEBUG_NO_QUAD_LOD) {
+         if (gallivm_perf & GALLIVM_PERF_NO_QUAD_LOD) {
             lod_property = LP_SAMPLER_LOD_PER_ELEMENT;
          }
          else {
@@ -2394,7 +2394,7 @@ emit_sample(struct lp_build_tgsi_soa_context *bld,
        * cases exist in practice.
        */
       if (bld->bld_base.info->processor == PIPE_SHADER_FRAGMENT) {
-         if (gallivm_debug & GALLIVM_DEBUG_NO_QUAD_LOD) {
+         if (gallivm_perf & GALLIVM_PERF_NO_QUAD_LOD) {
             lod_property = LP_SAMPLER_LOD_PER_ELEMENT;
          }
          else {