From f41b6cfb07ede2be053c57e38d4d6b9433f90bf1 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 7 Jan 2016 19:50:12 +0200 Subject: [PATCH] llvmpipe: use sse2 conv code for altivec In lp_build_conv() and lp_build_conv_auto(), there is a special case of conversion when sse2 is present. That code path is suitable without any changes to altivec, because all the functions that are called in that code path already support altivec. This patch increase the FPS in POWER arch across the board between 10%-25% I checked ipers, glxgears, glxspheres64, openarena, xonotic and glmark2. Signed-off-by: Oded Gabbay Reviewed-by: Roland Scheidegger --- src/gallium/auxiliary/gallivm/lp_bld_conv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/gallium/auxiliary/gallivm/lp_bld_conv.c b/src/gallium/auxiliary/gallivm/lp_bld_conv.c index 14244470c90..7854142f736 100644 --- a/src/gallium/auxiliary/gallivm/lp_bld_conv.c +++ b/src/gallium/auxiliary/gallivm/lp_bld_conv.c @@ -458,7 +458,7 @@ int lp_build_conv_auto(struct gallivm_state *gallivm, { /* Special case 4x4f --> 1x16ub */ if (src_type.length == 4 && - util_cpu_caps.has_sse2) + (util_cpu_caps.has_sse2 || util_cpu_caps.has_altivec)) { num_dsts = (num_srcs + 3) / 4; dst_type->length = num_srcs * 4 >= 16 ? 16 : num_srcs * 4; @@ -545,7 +545,7 @@ lp_build_conv(struct gallivm_state *gallivm, ((dst_type.length == 16 && 4 * num_dsts == num_srcs) || (num_dsts == 1 && dst_type.length * num_srcs == 16 && num_srcs != 3)) && - util_cpu_caps.has_sse2) + (util_cpu_caps.has_sse2 || util_cpu_caps.has_altivec)) { struct lp_build_context bld; struct lp_type int16_type, int32_type; -- 2.30.2