From: Kenneth Graunke <kenneth@whitecape.org>
Date: Thu, 17 Jul 2014 21:33:15 +0000 (-0700)
Subject: i965: Enable INTDIV in SIMD16 mode.
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=c66d928f2c9fa59e162c391fbdd37df969959718;p=mesa.git

i965: Enable INTDIV in SIMD16 mode.

All we need to do is decompose this to two SIMD8 instructions, like we
do in many other cases.  We even already have code for that.

I apparently just botched this last time I tried, and it was easy.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
---

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 8405502f433..35ada42c508 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -1404,18 +1404,6 @@ fs_visitor::emit_math(enum opcode opcode, fs_reg dst, fs_reg src0, fs_reg src1)
    int base_mrf = 2;
    fs_inst *inst;
 
-   switch (opcode) {
-   case SHADER_OPCODE_INT_QUOTIENT:
-   case SHADER_OPCODE_INT_REMAINDER:
-      if (brw->gen >= 7)
-	 no16("SIMD16 INTDIV unsupported\n");
-      break;
-   case SHADER_OPCODE_POW:
-      break;
-   default:
-      unreachable("not reached: unsupported binary math opcode.");
-   }
-
    if (brw->gen >= 8) {
       inst = emit(opcode, dst, src0, src1);
    } else if (brw->gen >= 6) {
diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index 9e260a7ffe7..1190f1f7e66 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -1620,9 +1620,9 @@ fs_generator::generate_code(exec_list *instructions)
       case SHADER_OPCODE_INT_REMAINDER:
       case SHADER_OPCODE_POW:
          assert(brw->gen < 6 || inst->mlen == 0);
-	 if (brw->gen >= 7) {
+	 if (brw->gen >= 7 && inst->opcode == SHADER_OPCODE_POW) {
             gen6_math(p, dst, brw_math_function(inst->opcode), src[0], src[1]);
-	 } else if (brw->gen == 6) {
+	 } else if (brw->gen >= 6) {
 	    generate_math_gen6(inst, dst, src[0], src[1]);
 	 } else {
 	    generate_math_gen4(inst, dst, src[0]);