[Mesa-dev] [PATCH 4/4] gallivm: dump bitcode before optimization

[sroland at vmware.com]

From: Roland Scheidegger <sroland at vmware.com>

If we dump the bitcode for off-line debug purposes, we really want the
pre-optimized bitcode, otherwise it's useless in identifying problems
with IR optimization (if you have a shader which takes an hour to do
IR optimization, it's also nice you don't have to wait that hour...).
Also, print out the function passes for opt which correspond to what
was used for jit compilation (and also the opt level for codegen).
Using opt/llc this way should then pretty much mimic what was done
for jit. (When specifying something like -time-passes
-debug-pass=[Structure|Arguments] (for either opt or llc) that also
gives very useful information in which passes all the time was spent,
and which passes are really run along with the order - llvm will add
passes due to dependencies on its own, and of course -O2 for llc
comes with a ~100 pass list.)
---
 src/gallium/auxiliary/gallivm/lp_bld_init.c | 35 +++++++++++++++++------------
 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_init.c b/src/gallium/auxiliary/gallivm/lp_bld_init.c
index d0afff1..41d828c 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_init.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_init.c
@@ -142,6 +142,10 @@ create_pass_manager(struct gallivm_state *gallivm)
        * TODO: Evaluate passes some more - keeping in mind
        * both quality of generated code and compile times.
        */
+      /*
+       * NOTE: if you change this, don't forget to change the output
+       * with GALLIVM_DEBUG_DUMP_BC in gallivm_compile_module.
+       */
       LLVMAddScalarReplAggregatesPass(gallivm->passmgr);
       LLVMAddEarlyCSEPass(gallivm->passmgr);
       LLVMAddCFGSimplificationPass(gallivm->passmgr);
@@ -151,7 +155,7 @@ create_pass_manager(struct gallivm_state *gallivm)
        * due to licm implying lcssa (since llvm 3.5), which can take forever.
        * Even for sane shaders, the cost of licm is rather high (and not just
        * due to lcssa, licm itself too), though mostly only in cases when it
-       * can actually move things, so having to disable it is a pity.   
+       * can actually move things, so having to disable it is a pity.
        * LLVMAddLICMPass(gallivm->passmgr);
        */
       LLVMAddReassociatePass(gallivm->passmgr);
@@ -597,6 +601,22 @@ gallivm_compile_module(struct gallivm_state *gallivm)
       gallivm->builder = NULL;
    }
 
+   /* Dump bitcode to a file */
+   if (gallivm_debug & GALLIVM_DEBUG_DUMP_BC) {
+      char filename[256];
+      assert(gallivm->module_name);
+      util_snprintf(filename, sizeof(filename), "ir_%s.bc", gallivm->module_name);
+      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" :
+                   "-sroa -early-cse -simplifycfg -reassociate "
+                   "-mem2reg -constprop -instcombine -gvn",
+                   filename, gallivm_debug & GALLIVM_DEBUG_NO_OPT ? 0 : 2,
+                   (HAVE_LLVM >= 0x0305) ? "[-mcpu=<-mcpu option>] " : "",
+                   "[-mattr=<-mattr option(s)>]");
+   }
+
    if (gallivm_debug & GALLIVM_DEBUG_PERF)
       time_begin = os_time_get();
 
@@ -630,19 +650,6 @@ gallivm_compile_module(struct gallivm_state *gallivm)
                    gallivm->module_name, time_msec);
    }
 
-   /* Dump byte code to a file */
-   if (gallivm_debug & GALLIVM_DEBUG_DUMP_BC) {
-      char filename[256];
-      assert(gallivm->module_name);
-      util_snprintf(filename, sizeof(filename), "ir_%s.bc", gallivm->module_name);
-      LLVMWriteBitcodeToFile(gallivm->module, filename);
-      debug_printf("%s written\n", filename);
-      debug_printf("Invoke as \"llc %s%s -o - %s\"\n",
-                   (HAVE_LLVM >= 0x0305) ? "[-mcpu=<-mcpu option>] " : "",
-                   "[-mattr=<-mattr option(s)>]",
-                   filename);
-   }
-
    if (use_mcjit) {
       /* Setting the module's DataLayout to an empty string will cause the
        * ExecutionEngine to copy to the DataLayout string from its target
-- 
2.7.4