vp8 fast quantizer with intrinsics
Reduce dependency on offsets file by using intrinsics. Disassembly shows
improvements over previous assembly specifically in register management,
preloading, and {pro,epi}log. Speed change is within margin of error.
Change-Id: I8131b4b4d62bc092407fe847bfaa8f2c0e1384ff
diff --git a/vp8/vp8cx.mk b/vp8/vp8cx.mk
index 0659407..f6feafb 100644
--- a/vp8/vp8cx.mk
+++ b/vp8/vp8cx.mk
@@ -89,8 +89,15 @@
VP8_CX_SRCS-$(HAVE_MMX) += encoder/x86/vp8_enc_stubs_mmx.c
VP8_CX_SRCS-$(HAVE_SSE2) += encoder/x86/dct_sse2.asm
VP8_CX_SRCS-$(HAVE_SSE2) += encoder/x86/fwalsh_sse2.asm
+VP8_CX_SRCS-$(HAVE_SSE2) += encoder/x86/quantize_sse2.c
VP8_CX_SRCS-$(HAVE_SSE2) += encoder/x86/quantize_sse2.asm
+# TODO(johann) make this generic
+ifeq ($(HAVE_SSE2),yes)
+vp8/encoder/x86/quantize_sse2.c.o: CFLAGS += -msse2
+vp8/encoder/x86/quantize_sse2.c.d: CFLAGS += -msse2
+endif
+
ifeq ($(CONFIG_TEMPORAL_DENOISING),yes)
VP8_CX_SRCS-$(HAVE_SSE2) += encoder/x86/denoising_sse2.c
ifeq ($(HAVE_SSE2),yes)
@@ -112,7 +119,6 @@
VP8_CX_SRCS_REMOVE-$(HAVE_SSE2) += encoder/x86/temporal_filter_apply_sse2.asm
endif
-
VP8_CX_SRCS-yes := $(filter-out $(VP8_CX_SRCS_REMOVE-yes),$(VP8_CX_SRCS-yes))
$(eval $(call asm_offsets_template,\
