Emulation/ppsspp
1
0
Fork 0
mirror of https://github.com/hrydgard/ppsspp.git synced 2025-04-02 11:01:50 -04:00
Code Issues Projects Releases Packages Wiki Activity

Add uv range to arm64 and non-jit decoders.

Browse source
This commit is contained in:
Unknown W. Brackets 2015-07-19 15:59:10 -07:00
parent 5c233fa545
commit 72a73045bb
2 changed files with 37 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
GPU/Common/VertexDecoderArm64.cpp
View file

@ -554,7 +554,27 @@ void VertexDecoderJitCache::Jit_TcU16() {
}
void VertexDecoderJitCache::Jit_TcU16Through() {
LDUR(tempReg1, srcReg, dec_->tcoff);
LDRH(INDEX_UNSIGNED, tempReg1, srcReg, dec_->tcoff);
LDRH(INDEX_UNSIGNED, tempReg2, srcReg, dec_->tcoff + 2);
// TODO: Cleanup.
MOVP2R(scratchReg64, &gstate_c.vertMinU);
auto updateSide = [&](ARM64Reg r, CCFlags cc, u32 off) {
LDRH(INDEX_UNSIGNED, tempReg3, scratchReg64, off);
CMP(r, tempReg3);
FixupBranch skip = B(InvertCond(cc));
STRH(INDEX_UNSIGNED, r, scratchReg64, off);
SetJumpTarget(skip);
};
// TODO: Can this actually be fast? Hmm, floats aren't better.
updateSide(tempReg1, CC_LT, 0);
updateSide(tempReg1, CC_GT, 2);
updateSide(tempReg2, CC_LT, 4);
updateSide(tempReg2, CC_GT, 6);
ORR(tempReg1, tempReg1, tempReg2, ArithOption(tempReg2, ST_LSL, 16));
STR(INDEX_UNSIGNED, tempReg1, dstReg, dec_->decFmt.uvoff);
}

16
GPU/Common/VertexDecoderCommon.cpp
View file

@ -15,6 +15,7 @@
// Official git repository and contact information can be found at
// https://github.com/hrydgard/ppsspp and http://www.ppsspp.org/.
#include <algorithm>
#include <stdio.h>
#include "base/basictypes.h"
@ -294,6 +295,11 @@ void VertexDecoder::Step_TcU16Through() const
const u16 *uvdata = (const u16_le*)(ptr_ + tcoff);
uv[0] = uvdata[0];
uv[1] = uvdata[1];
gstate_c.vertMinU = std::min(gstate_c.vertMinU, uvdata[0]);
gstate_c.vertMaxU = std::max(gstate_c.vertMaxU, uvdata[0]);
gstate_c.vertMinV = std::min(gstate_c.vertMinV, uvdata[1]);
gstate_c.vertMaxV = std::max(gstate_c.vertMaxV, uvdata[1]);
}
void VertexDecoder::Step_TcU16ThroughDouble() const
@ -318,6 +324,11 @@ void VertexDecoder::Step_TcU16ThroughToFloat() const
const u16 *uvdata = (const u16_le*)(ptr_ + tcoff);
uv[0] = uvdata[0];
uv[1] = uvdata[1];
gstate_c.vertMinU = std::min(gstate_c.vertMinU, uvdata[0]);
gstate_c.vertMaxU = std::max(gstate_c.vertMaxU, uvdata[0]);
gstate_c.vertMinV = std::min(gstate_c.vertMinV, uvdata[1]);
gstate_c.vertMaxV = std::max(gstate_c.vertMaxV, uvdata[1]);
}
void VertexDecoder::Step_TcU16ThroughDoubleToFloat() const
@ -342,6 +353,11 @@ void VertexDecoder::Step_TcFloatThrough() const
const float *uvdata = (const float*)(ptr_ + tcoff);
uv[0] = uvdata[0];
uv[1] = uvdata[1];
gstate_c.vertMinU = std::min(gstate_c.vertMinU, (u16)uvdata[0]);
gstate_c.vertMaxU = std::max(gstate_c.vertMaxU, (u16)uvdata[0]);
gstate_c.vertMinV = std::min(gstate_c.vertMinV, (u16)uvdata[1]);
gstate_c.vertMaxV = std::max(gstate_c.vertMaxV, (u16)uvdata[1]);
}
void VertexDecoder::Step_TcU8Prescale() const {