Mesa (staging/19.2): gallivm: Fix saturated signed psub/padd intrinsics on llvm 8

[GitLab Mirror]

Module: Mesa
Branch: staging/19.2
Commit: 16af8e977232dc1b546bea8a973725c341639577
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=16af8e977232dc1b546bea8a973725c341639577

Author: Roland Scheidegger <sroland at vmware.com>
Date:   Thu Oct 17 04:14:28 2019 +0200

gallivm: Fix saturated signed psub/padd intrinsics on llvm 8

LLVM 8 did remove both the signed and unsigned sse2/avx intrinsics in
the end, and provide arch-independent llvm intrinsics instead.
Fixes a crash when using snorm framebuffers (tested with piglit
arb_color_buffer_float-render GL_RGBA8_SNORM -auto).

Reviewed-by: Jose Fonseca <jfonseca at vmware.com>
Reviewed-by: Dave Airlie <airlied at redhat.com>
CC: <mesa-stable at lists.freedesktop.org>
(cherry picked from commit 045f05a2f68c301c850a38a511c8e254080fce9a)
Conflicts resolved by Dylan Baker

---

 src/gallium/auxiliary/gallivm/lp_bld_arit.c | 28 ++++++++++------------------
 1 file changed, 10 insertions(+), 18 deletions(-)

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_arit.c b/src/gallium/auxiliary/gallivm/lp_bld_arit.c
index c4931c0b230..14289ee2ba5 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_arit.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_arit.c
@@ -555,7 +555,7 @@ lp_build_add(struct lp_build_context *bld,
         return bld->one;
 
       if (!type.floating && !type.fixed) {
-         if (HAVE_LLVM >= 0x0900) {
+         if (HAVE_LLVM >= 0x0800) {
             char intrin[32];
             intrinsic = type.sign ? "llvm.sadd.sat" : "llvm.uadd.sat";
             lp_format_intrinsic(intrin, sizeof intrin, intrinsic, bld->vec_type);
@@ -564,11 +564,9 @@ lp_build_add(struct lp_build_context *bld,
          if (type.width * type.length == 128) {
             if (util_cpu_caps.has_sse2) {
                if (type.width == 8)
-                 intrinsic = type.sign ? "llvm.x86.sse2.padds.b" :
-                                         HAVE_LLVM < 0x0800 ? "llvm.x86.sse2.paddus.b" : NULL;
+                 intrinsic = type.sign ? "llvm.x86.sse2.padds.b" : "llvm.x86.sse2.paddus.b";
                if (type.width == 16)
-                 intrinsic = type.sign ? "llvm.x86.sse2.padds.w" :
-                                         HAVE_LLVM < 0x0800 ? "llvm.x86.sse2.paddus.w" : NULL;
+                 intrinsic = type.sign ? "llvm.x86.sse2.padds.w" : "llvm.x86.sse2.paddus.w";
             } else if (util_cpu_caps.has_altivec) {
                if (type.width == 8)
                   intrinsic = type.sign ? "llvm.ppc.altivec.vaddsbs" : "llvm.ppc.altivec.vaddubs";
@@ -579,11 +577,9 @@ lp_build_add(struct lp_build_context *bld,
          if (type.width * type.length == 256) {
             if (util_cpu_caps.has_avx2) {
                if (type.width == 8)
-                  intrinsic = type.sign ? "llvm.x86.avx2.padds.b" :
-                                          HAVE_LLVM < 0x0800 ? "llvm.x86.avx2.paddus.b" : NULL;
+                  intrinsic = type.sign ? "llvm.x86.avx2.padds.b" : "llvm.x86.avx2.paddus.b";
                if (type.width == 16)
-                  intrinsic = type.sign ? "llvm.x86.avx2.padds.w" :
-                                          HAVE_LLVM < 0x0800 ? "llvm.x86.avx2.paddus.w" : NULL;
+                  intrinsic = type.sign ? "llvm.x86.avx2.padds.w" : "llvm.x86.avx2.paddus.w";
             }
          }
       }
@@ -883,7 +879,7 @@ lp_build_sub(struct lp_build_context *bld,
         return bld->zero;
 
       if (!type.floating && !type.fixed) {
-         if (HAVE_LLVM >= 0x0900) {
+         if (HAVE_LLVM >= 0x0800) {
             char intrin[32];
             intrinsic = type.sign ? "llvm.ssub.sat" : "llvm.usub.sat";
             lp_format_intrinsic(intrin, sizeof intrin, intrinsic, bld->vec_type);
@@ -892,11 +888,9 @@ lp_build_sub(struct lp_build_context *bld,
          if (type.width * type.length == 128) {
             if (util_cpu_caps.has_sse2) {
                if (type.width == 8)
-                  intrinsic = type.sign ? "llvm.x86.sse2.psubs.b" :
-                                          HAVE_LLVM < 0x0800 ? "llvm.x86.sse2.psubus.b" : NULL;
+                  intrinsic = type.sign ? "llvm.x86.sse2.psubs.b" : "llvm.x86.sse2.psubus.b";
                if (type.width == 16)
-                  intrinsic = type.sign ? "llvm.x86.sse2.psubs.w" :
-                                          HAVE_LLVM < 0x0800 ? "llvm.x86.sse2.psubus.w" : NULL;
+                  intrinsic = type.sign ? "llvm.x86.sse2.psubs.w" : "llvm.x86.sse2.psubus.w";
             } else if (util_cpu_caps.has_altivec) {
                if (type.width == 8)
                   intrinsic = type.sign ? "llvm.ppc.altivec.vsubsbs" : "llvm.ppc.altivec.vsububs";
@@ -907,11 +901,9 @@ lp_build_sub(struct lp_build_context *bld,
          if (type.width * type.length == 256) {
             if (util_cpu_caps.has_avx2) {
                if (type.width == 8)
-                  intrinsic = type.sign ? "llvm.x86.avx2.psubs.b" :
-                                          HAVE_LLVM < 0x0800 ? "llvm.x86.avx2.psubus.b" : NULL;
+                  intrinsic = type.sign ? "llvm.x86.avx2.psubs.b" : "llvm.x86.avx2.psubus.b";
                if (type.width == 16)
-                  intrinsic = type.sign ? "llvm.x86.avx2.psubs.w" :
-                                          HAVE_LLVM < 0x0800 ? "llvm.x86.avx2.psubus.w" : NULL;
+                  intrinsic = type.sign ? "llvm.x86.avx2.psubs.w" : "llvm.x86.avx2.psubus.w";
             }
          }
       }