[Mesa-dev] [PATCH 05/15] ac: revert new LLVM 7.0 behavior for fdiv

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

Cc: 18.1 18.2 <mesa-stable at 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.
-- 
2.17.1