From 50b8c2527464dbe18a01ab6412de4465cebf2225 Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Wed, 26 Feb 2020 15:04:38 +0100 Subject: [PATCH] ac/llvm: fix 64-bit fmed3 Lower 64-bit fmed3 because LLVM doesn't expose an intrinsic. Fixes dEQP-VK.spirv_assembly.instruction.amd_trinary_minmax.mid3.f64.*. Fixes: d6a07732c9c ("ac: use llvm.amdgcn.fmed3 intrinsic for nir_op_fmed3") Signed-off-by: Samuel Pitoiset Reviewed-by: Bas Nieuwenhuizen Part-of: --- src/amd/llvm/ac_llvm_build.c | 48 +++++++++++++++++++++++------------- 1 file changed, 31 insertions(+), 17 deletions(-) diff --git a/src/amd/llvm/ac_llvm_build.c b/src/amd/llvm/ac_llvm_build.c index 8d706944a45..db7964d6aa9 100644 --- a/src/amd/llvm/ac_llvm_build.c +++ b/src/amd/llvm/ac_llvm_build.c @@ -2723,27 +2723,41 @@ LLVMValueRef ac_build_fmed3(struct ac_llvm_context *ctx, LLVMValueRef src0, LLVMValueRef src1, LLVMValueRef src2, unsigned bitsize) { - LLVMTypeRef type; - char *intr; + LLVMValueRef result; - if (bitsize == 16) { - intr = "llvm.amdgcn.fmed3.f16"; - type = ctx->f16; - } else if (bitsize == 32) { - intr = "llvm.amdgcn.fmed3.f32"; - type = ctx->f32; + if (bitsize == 64) { + /* Lower 64-bit fmed because LLVM doesn't expose an intrinsic. */ + LLVMValueRef min1, min2, max1; + + min1 = ac_build_fmin(ctx, src0, src1); + max1 = ac_build_fmax(ctx, src0, src1); + min2 = ac_build_fmin(ctx, max1, src2); + + result = ac_build_fmax(ctx, min2, min1); } else { - intr = "llvm.amdgcn.fmed3.f64"; - type = ctx->f64; + LLVMTypeRef type; + char *intr; + + if (bitsize == 16) { + intr = "llvm.amdgcn.fmed3.f16"; + type = ctx->f16; + } else { + assert(bitsize == 32); + intr = "llvm.amdgcn.fmed3.f32"; + type = ctx->f32; + } + + LLVMValueRef params[] = { + src0, + src1, + src2, + }; + + result = ac_build_intrinsic(ctx, intr, type, params, 3, + AC_FUNC_ATTR_READNONE); } - LLVMValueRef params[] = { - src0, - src1, - src2, - }; - return ac_build_intrinsic(ctx, intr, type, params, 3, - AC_FUNC_ATTR_READNONE); + return result; } LLVMValueRef ac_build_fract(struct ac_llvm_context *ctx, LLVMValueRef src0, -- 2.30.2