[Mesa-dev] [PATCH v3 5/6] gm107/ir: add LIMM form of mad

[Karol Herbst]

v2: renamed commit
    reordered modifiers
    add assert(dst == src2)
v3: reordered modifiers again

Signed-off-by: Karol Herbst <karolherbst at gmail.com>
---
 .../drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp | 35 ++++++++++++++++------
 .../drivers/nouveau/codegen/nv50_ir_peephole.cpp   |  3 +-
 2 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
index 5ed2ad4..d778e86 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
@@ -1306,7 +1306,7 @@ CodeEmitterGM107::emitFMUL()
 void
 CodeEmitterGM107::emitFFMA()
 {
-   /*XXX: ffma32i exists, but not using it as third src overlaps dst */
+   bool isLongIMMD = false;
    switch(insn->src(2).getFile()) {
    case FILE_GPR:
       switch (insn->src(1).getFile()) {
@@ -1319,14 +1319,22 @@ CodeEmitterGM107::emitFFMA()
          emitCBUF(0x22, -1, 0x14, 16, 2, insn->src(1));
          break;
       case FILE_IMMEDIATE:
-         emitInsn(0x32800000);
-         emitIMMD(0x14, 19, insn->src(1));
+         if (longIMMD(insn->getSrc(1))) {
+            assert(insn->getDef(0)->reg.data.id == insn->getSrc(2)->reg.data.id);
+            isLongIMMD = true;
+            emitInsn(0x0c000000);
+            emitIMMD(0x14, 32, insn->src(1));
+         } else {
+            emitInsn(0x32800000);
+            emitIMMD(0x14, 19, insn->src(1));
+         }
          break;
       default:
          assert(!"bad src1 file");
          break;
       }
-      emitGPR (0x27, insn->src(2));
+      if (!isLongIMMD)
+         emitGPR (0x27, insn->src(2));
       break;
    case FILE_MEMORY_CONST:
       emitInsn(0x51800000);
@@ -1337,11 +1345,20 @@ CodeEmitterGM107::emitFFMA()
       assert(!"bad src2 file");
       break;
    }
-   emitRND (0x33);
-   emitSAT (0x32);
-   emitNEG (0x31, insn->src(2));
-   emitNEG2(0x30, insn->src(0), insn->src(1));
-   emitCC  (0x2f);
+
+   emitRND(0x33);
+
+   if (isLongIMMD) {
+      emitNEG (0x39, insn->src(2));
+      emitNEG2(0x38, insn->src(0), insn->src(1));
+      emitSAT (0x37);
+      emitCC  (0x34);
+   } else {
+      emitSAT (0x32);
+      emitNEG (0x31, insn->src(2));
+      emitNEG2(0x30, insn->src(0), insn->src(1));
+      emitCC  (0x2f);
+   }
 
    emitFMZ(0x35, 2);
    emitGPR(0x08, insn->src(0));
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 2ddabf7..959f708 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -3599,8 +3599,7 @@ bool
 Program::optimizePostRA(int level)
 {
    RUN_PASS(2, FlatteningPass, run);
-   if (getTarget()->getChipset() < NVISA_GM107_CHIPSET)
-      RUN_PASS(2, PostRaConstantFolding, run);
+   RUN_PASS(2, PostRaConstantFolding, run);
 
    return true;
 }
-- 
2.10.1