llvmpipe: use vpkswss when dst is signed

This patch fixes a bug when building a pack instruction.

For POWER (altivec), in case the destination is signed and the
src width is 32, we need to use vpkswss. The original code used vpkuwus,
which emits an unsigned result.

This fixes the following piglit tests on ppc64le:
- spec@arb_color_buffer_float@gl_rgba8-drawpixels
- shaders@glsl-fs-fogscale

I've also corrected some coding style issues in the function.

v2: Returned else statements to vmware style

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_pack.c b/src/gallium/auxiliary/gallivm/lp_bld_pack.c
index cdf6d80c2611553a49f269c08753b0ddffe31f79..0b0f7f0147cb28f8a2d75e4dcc5e8e651d7890a7 100644 (file)
--- a/src/gallium/auxiliary/gallivm/lp_bld_pack.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_pack.c
@@ -461,50 +461,49 @@ lp_build_pack2(struct gallivm_state *gallivm,
    assert(src_type.length * 2 == dst_type.length);
 
    /* Check for special cases first */
-   if((util_cpu_caps.has_sse2 || util_cpu_caps.has_altivec) &&
-       src_type.width * src_type.length >= 128) {
+   if ((util_cpu_caps.has_sse2 || util_cpu_caps.has_altivec) &&
+        src_type.width * src_type.length >= 128) {
       const char *intrinsic = NULL;
       boolean swap_intrinsic_operands = FALSE;
 
       switch(src_type.width) {
       case 32:
          if (util_cpu_caps.has_sse2) {
-           if(dst_type.sign) {
+           if (dst_type.sign) {
               intrinsic = "llvm.x86.sse2.packssdw.128";
-           }
-           else {
+           } else {
               if (util_cpu_caps.has_sse4_1) {
                  intrinsic = "llvm.x86.sse41.packusdw";
               }
            }
          } else if (util_cpu_caps.has_altivec) {
             if (dst_type.sign) {
-              intrinsic = "llvm.ppc.altivec.vpkswus";
-           } else {
-              intrinsic = "llvm.ppc.altivec.vpkuwus";
-           }
+               intrinsic = "llvm.ppc.altivec.vpkswss";
+            } else {
+               intrinsic = "llvm.ppc.altivec.vpkuwus";
+            }
 #ifdef PIPE_ARCH_LITTLE_ENDIAN
-           swap_intrinsic_operands = TRUE;
+            swap_intrinsic_operands = TRUE;
 #endif
          }
          break;
       case 16:
          if (dst_type.sign) {
             if (util_cpu_caps.has_sse2) {
-              intrinsic = "llvm.x86.sse2.packsswb.128";
+               intrinsic = "llvm.x86.sse2.packsswb.128";
             } else if (util_cpu_caps.has_altivec) {
-              intrinsic = "llvm.ppc.altivec.vpkshss";
+               intrinsic = "llvm.ppc.altivec.vpkshss";
 #ifdef PIPE_ARCH_LITTLE_ENDIAN
-              swap_intrinsic_operands = TRUE;
+               swap_intrinsic_operands = TRUE;
 #endif
             }
          } else {
             if (util_cpu_caps.has_sse2) {
-              intrinsic = "llvm.x86.sse2.packuswb.128";
+               intrinsic = "llvm.x86.sse2.packuswb.128";
             } else if (util_cpu_caps.has_altivec) {
-             intrinsic = "llvm.ppc.altivec.vpkshus";
+               intrinsic = "llvm.ppc.altivec.vpkshus";
 #ifdef PIPE_ARCH_LITTLE_ENDIAN
-              swap_intrinsic_operands = TRUE;
+               swap_intrinsic_operands = TRUE;
 #endif
             }
          }