Hi Marek,

It's late and I haven't dug into this any further but this patch causes a whole bunch of f64 piglit tests to fail for the radeonsi nir backend.

e.g.

./bin/shader_runner generated_tests/spec/glsl-4.00/execution/built-in-functions/fs-inverse-dmat2.shader_test -auto -fbo


LLVM ERROR: Cannot select: 0x7fbc48075aa8: f64 = bitcast 0x7fbc48077730
  0x7fbc48077730: f32 = RCP 0x7fbc4806e788
    0x7fbc4806e788: f64 = fadd nsz 0x7fbc480757d0, 0x7fbc48075a40
      0x7fbc480757d0: f64 = fmul nsz 0x7fbc4806f0e0, 0x7fbc4806f420
        0x7fbc4806f0e0: f64 = bitcast 0x7fbc4806f078

On 30/8/18 6:13 am, Marek Olšák wrote:
From: Marek Olšák <marek.ol...@amd.com>

Cc: 18.1 18.2 <mesa-sta...@lists.freedesktop.org>
---
  src/amd/common/ac_llvm_build.c | 9 ++++++++-
  1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/src/amd/common/ac_llvm_build.c b/src/amd/common/ac_llvm_build.c
index c741a1ab62d..629cd2a7527 100644
--- a/src/amd/common/ac_llvm_build.c
+++ b/src/amd/common/ac_llvm_build.c
@@ -554,21 +554,28 @@ LLVMValueRef ac_build_expand_to_vec4(struct 
ac_llvm_context *ctx,
                chan[num_channels++] = LLVMGetUndef(elemtype);
return ac_build_gather_values(ctx, chan, 4);
  }
LLVMValueRef
  ac_build_fdiv(struct ac_llvm_context *ctx,
              LLVMValueRef num,
              LLVMValueRef den)
  {
-       LLVMValueRef ret = LLVMBuildFDiv(ctx->builder, num, den, "");
+       /* If we do (num / den), LLVM >= 7.0 does:
+        *    return num * v_rcp_f32(den * (fabs(den) > 0x1.0p+96f ? 0x1.0p-32f 
: 1.0f));
+        *
+        * If we do (num * (1 / den)), LLVM does:
+        *    return num * v_rcp_f32(den);
+        */
+       LLVMValueRef rcp = LLVMBuildFDiv(ctx->builder, ctx->f32_1, den, "");
+       LLVMValueRef ret = LLVMBuildFMul(ctx->builder, num, rcp, "");
/* Use v_rcp_f32 instead of precise division. */
        if (!LLVMIsConstant(ret))
                LLVMSetMetadata(ret, ctx->fpmath_md_kind, 
ctx->fpmath_md_2p5_ulp);
        return ret;
  }
/* Coordinates for cube map selection. sc, tc, and ma are as in Table 8.27
   * of the OpenGL 4.5 (Compatibility Profile) specification, except ma is
   * already multiplied by two. id is the cube face number.

_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev

Reply via email to