diff options
Diffstat (limited to 'src/gallium/auxiliary/tgsi')
-rw-r--r-- | src/gallium/auxiliary/tgsi/tgsi-instruction-set.txt | 1127 | ||||
-rw-r--r-- | src/gallium/auxiliary/tgsi/tgsi_scan.c | 32 | ||||
-rw-r--r-- | src/gallium/auxiliary/tgsi/tgsi_scan.h | 3 | ||||
-rw-r--r-- | src/gallium/auxiliary/tgsi/tgsi_sse2.c | 32 | ||||
-rw-r--r-- | src/gallium/auxiliary/tgsi/tgsi_util.c | 146 | ||||
-rw-r--r-- | src/gallium/auxiliary/tgsi/tgsi_util.h | 5 |
6 files changed, 182 insertions, 1163 deletions
diff --git a/src/gallium/auxiliary/tgsi/tgsi-instruction-set.txt b/src/gallium/auxiliary/tgsi/tgsi-instruction-set.txt deleted file mode 100644 index 5d9eed9258..0000000000 --- a/src/gallium/auxiliary/tgsi/tgsi-instruction-set.txt +++ /dev/null @@ -1,1127 +0,0 @@ -TGSI Instruction Specification -============================== -============================== - - -1 Instruction Set Operations -============================= - - -1.1 GL_NV_vertex_program -------------------------- - - -1.1.1 ARL - Address Register Load - - dst.x = floor(src.x) - dst.y = floor(src.y) - dst.z = floor(src.z) - dst.w = floor(src.w) - - -1.1.2 MOV - Move - - dst.x = src.x - dst.y = src.y - dst.z = src.z - dst.w = src.w - - -1.1.3 LIT - Light Coefficients - - dst.x = 1.0 - dst.y = max(src.x, 0.0) - dst.z = (src.x > 0.0) ? pow(max(src.y, 0.0), clamp(src.w, -128.0, 128.0)) : 0.0 - dst.w = 1.0 - - -1.1.4 RCP - Reciprocal - - dst.x = 1.0 / src.x - dst.y = 1.0 / src.x - dst.z = 1.0 / src.x - dst.w = 1.0 / src.x - - -1.1.5 RSQ - Reciprocal Square Root - - dst.x = 1.0 / sqrt(abs(src.x)) - dst.y = 1.0 / sqrt(abs(src.x)) - dst.z = 1.0 / sqrt(abs(src.x)) - dst.w = 1.0 / sqrt(abs(src.x)) - - -1.1.6 EXP - Approximate Exponential Base 2 - - dst.x = pow(2.0, floor(src.x)) - dst.y = src.x - floor(src.x) - dst.z = pow(2.0, src.x) - dst.w = 1.0 - - -1.1.7 LOG - Approximate Logarithm Base 2 - - dst.x = floor(lg2(abs(src.x))) - dst.y = abs(src.x) / pow(2.0, floor(lg2(abs(src.x)))) - dst.z = lg2(abs(src.x)) - dst.w = 1.0 - - -1.1.8 MUL - Multiply - - dst.x = src0.x * src1.x - dst.y = src0.y * src1.y - dst.z = src0.z * src1.z - dst.w = src0.w * src1.w - - -1.1.9 ADD - Add - - dst.x = src0.x + src1.x - dst.y = src0.y + src1.y - dst.z = src0.z + src1.z - dst.w = src0.w + src1.w - - -1.1.10 DP3 - 3-component Dot Product - - dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z - dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z - dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z - dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z - - -1.1.11 DP4 - 4-component Dot Product - - dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w - dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w - dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w - dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w - - -1.1.12 DST - Distance Vector - - dst.x = 1.0 - dst.y = src0.y * src1.y - dst.z = src0.z - dst.w = src1.w - - -1.1.13 MIN - Minimum - - dst.x = min(src0.x, src1.x) - dst.y = min(src0.y, src1.y) - dst.z = min(src0.z, src1.z) - dst.w = min(src0.w, src1.w) - - -1.1.14 MAX - Maximum - - dst.x = max(src0.x, src1.x) - dst.y = max(src0.y, src1.y) - dst.z = max(src0.z, src1.z) - dst.w = max(src0.w, src1.w) - - -1.1.15 SLT - Set On Less Than - - dst.x = (src0.x < src1.x) ? 1.0 : 0.0 - dst.y = (src0.y < src1.y) ? 1.0 : 0.0 - dst.z = (src0.z < src1.z) ? 1.0 : 0.0 - dst.w = (src0.w < src1.w) ? 1.0 : 0.0 - - -1.1.16 SGE - Set On Greater Equal Than - - dst.x = (src0.x >= src1.x) ? 1.0 : 0.0 - dst.y = (src0.y >= src1.y) ? 1.0 : 0.0 - dst.z = (src0.z >= src1.z) ? 1.0 : 0.0 - dst.w = (src0.w >= src1.w) ? 1.0 : 0.0 - - -1.1.17 MAD - Multiply And Add - - dst.x = src0.x * src1.x + src2.x - dst.y = src0.y * src1.y + src2.y - dst.z = src0.z * src1.z + src2.z - dst.w = src0.w * src1.w + src2.w - - -1.2 GL_ATI_fragment_shader ---------------------------- - - -1.2.1 SUB - Subtract - - dst.x = src0.x - src1.x - dst.y = src0.y - src1.y - dst.z = src0.z - src1.z - dst.w = src0.w - src1.w - - -1.2.2 DOT3 - 3-component Dot Product - - Alias for DP3. - - -1.2.3 DOT4 - 4-component Dot Product - - Alias for DP4. - - -1.2.4 LERP - Linear Interpolate - - dst.x = src0.x * (src1.x - src2.x) + src2.x - dst.y = src0.y * (src1.y - src2.y) + src2.y - dst.z = src0.z * (src1.z - src2.z) + src2.z - dst.w = src0.w * (src1.w - src2.w) + src2.w - - -1.2.5 CND - Condition - - dst.x = (src2.x > 0.5) ? src0.x : src1.x - dst.y = (src2.y > 0.5) ? src0.y : src1.y - dst.z = (src2.z > 0.5) ? src0.z : src1.z - dst.w = (src2.w > 0.5) ? src0.w : src1.w - - -1.2.6 CND0 - Condition Zero - - Removed. Use (CMP src2, src1, src0) instead. - -1.2.7 DOT2ADD - 2-component Dot Product And Add - - dst.x = src0.x * src1.x + src0.y * src1.y + src2.x - dst.y = src0.x * src1.x + src0.y * src1.y + src2.x - dst.z = src0.x * src1.x + src0.y * src1.y + src2.x - dst.w = src0.x * src1.x + src0.y * src1.y + src2.x - - -1.3 GL_EXT_vertex_shader -------------------------- - - -1.3.1 INDEX - Array Lookup - - Considered for removal from language. - - -1.3.2 NEGATE - Negate - - Considered for removal from language. - - -1.3.3 MADD - Multiply And Add - - Alias for MAD. - - -1.3.4 FRAC - Fraction - - dst.x = src.x - floor(src.x) - dst.y = src.y - floor(src.y) - dst.z = src.z - floor(src.z) - dst.w = src.w - floor(src.w) - - -1.3.5 SETGE - Set On Greater Equal - - Alias for SGE. - - -1.3.6 SETLT - Set On Less Than - - Alias for SLT. - - -1.3.7 CLAMP - Clamp - - dst.x = clamp(src0.x, src1.x, src2.x) - dst.y = clamp(src0.y, src1.y, src2.y) - dst.z = clamp(src0.z, src1.z, src2.z) - dst.w = clamp(src0.w, src1.w, src2.w) - - -1.3.8 FLOOR - Floor - - dst.x = floor(src.x) - dst.y = floor(src.y) - dst.z = floor(src.z) - dst.w = floor(src.w) - - -1.3.9 ROUND - Round - - dst.x = round(src.x) - dst.y = round(src.y) - dst.z = round(src.z) - dst.w = round(src.w) - - -1.3.10 EXPBASE2 - Exponential Base 2 - - dst.x = pow(2.0, src.x) - dst.y = pow(2.0, src.x) - dst.z = pow(2.0, src.x) - dst.w = pow(2.0, src.x) - - -1.3.11 LOGBASE2 - Logarithm Base 2 - - dst.x = lg2(src.x) - dst.y = lg2(src.x) - dst.z = lg2(src.x) - dst.w = lg2(src.x) - - -1.3.12 POWER - Power - - dst.x = pow(src0.x, src1.x) - dst.y = pow(src0.x, src1.x) - dst.z = pow(src0.x, src1.x) - dst.w = pow(src0.x, src1.x) - - -1.3.13 RECIP - Reciprocal - - Alias for RCP. - - -1.3.14 RECIPSQRT - Reciprocal Square Root - - Alias for RSQ. - - -1.3.15 CROSSPRODUCT - Cross Product - - dst.x = src0.y * src1.z - src1.y * src0.z - dst.y = src0.z * src1.x - src1.z * src0.x - dst.z = src0.x * src1.y - src1.x * src0.y - dst.w = 1.0 - - -1.3.16 MULTIPLYMATRIX - Multiply Matrix - - Considered for removal from language. - - -1.4 GL_NV_vertex_program1_1 ----------------------------- - - -1.4.1 ABS - Absolute - - dst.x = abs(src.x) - dst.y = abs(src.y) - dst.z = abs(src.z) - dst.w = abs(src.w) - - -1.4.2 RCC - Reciprocal Clamped - - dst.x = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020) - dst.y = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020) - dst.z = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020) - dst.w = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020) - - -1.4.3 DPH - Homogeneous Dot Product - - dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w - dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w - dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w - dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w - - -1.5 GL_NV_fragment_program ---------------------------- - - -1.5.1 COS - Cosine - - dst.x = cos(src.x) - dst.y = cos(src.x) - dst.z = cos(src.x) - dst.w = cos(src.w) - - -1.5.2 DDX - Derivative Relative To X - - dst.x = partialx(src.x) - dst.y = partialx(src.y) - dst.z = partialx(src.z) - dst.w = partialx(src.w) - - -1.5.3 DDY - Derivative Relative To Y - - dst.x = partialy(src.x) - dst.y = partialy(src.y) - dst.z = partialy(src.z) - dst.w = partialy(src.w) - - -1.5.4 EX2 - Exponential Base 2 - - Alias for EXPBASE2. - - -1.5.5 FLR - Floor - - Alias for FLOOR. - - -1.5.6 FRC - Fraction - - Alias for FRAC. - - -1.5.7 KILP - Predicated Discard - - discard - - -1.5.8 LG2 - Logarithm Base 2 - - Alias for LOGBASE2. - - -1.5.9 LRP - Linear Interpolate - - Alias for LERP. - - -1.5.10 PK2H - Pack Two 16-bit Floats - - TBD - - -1.5.11 PK2US - Pack Two Unsigned 16-bit Scalars - - TBD - - -1.5.12 PK4B - Pack Four Signed 8-bit Scalars - - TBD - - -1.5.13 PK4UB - Pack Four Unsigned 8-bit Scalars - - TBD - - -1.5.14 POW - Power - - Alias for POWER. - - -1.5.15 RFL - Reflection Vector - - dst.x = 2.0 * (src0.x * src1.x + src0.y * src1.y + src0.z * src1.z) / (src0.x * src0.x + src0.y * src0.y + src0.z * src0.z) * src0.x - src1.x - dst.y = 2.0 * (src0.x * src1.x + src0.y * src1.y + src0.z * src1.z) / (src0.x * src0.x + src0.y * src0.y + src0.z * src0.z) * src0.y - src1.y - dst.z = 2.0 * (src0.x * src1.x + src0.y * src1.y + src0.z * src1.z) / (src0.x * src0.x + src0.y * src0.y + src0.z * src0.z) * src0.z - src1.z - dst.w = 1.0 - - -1.5.16 SEQ - Set On Equal - - dst.x = (src0.x == src1.x) ? 1.0 : 0.0 - dst.y = (src0.y == src1.y) ? 1.0 : 0.0 - dst.z = (src0.z == src1.z) ? 1.0 : 0.0 - dst.w = (src0.w == src1.w) ? 1.0 : 0.0 - - -1.5.17 SFL - Set On False - - dst.x = 0.0 - dst.y = 0.0 - dst.z = 0.0 - dst.w = 0.0 - - -1.5.18 SGT - Set On Greater Than - - dst.x = (src0.x > src1.x) ? 1.0 : 0.0 - dst.y = (src0.y > src1.y) ? 1.0 : 0.0 - dst.z = (src0.z > src1.z) ? 1.0 : 0.0 - dst.w = (src0.w > src1.w) ? 1.0 : 0.0 - - -1.5.19 SIN - Sine - - dst.x = sin(src.x) - dst.y = sin(src.x) - dst.z = sin(src.x) - dst.w = sin(src.w) - - -1.5.20 SLE - Set On Less Equal Than - - dst.x = (src0.x <= src1.x) ? 1.0 : 0.0 - dst.y = (src0.y <= src1.y) ? 1.0 : 0.0 - dst.z = (src0.z <= src1.z) ? 1.0 : 0.0 - dst.w = (src0.w <= src1.w) ? 1.0 : 0.0 - - -1.5.21 SNE - Set On Not Equal - - dst.x = (src0.x != src1.x) ? 1.0 : 0.0 - dst.y = (src0.y != src1.y) ? 1.0 : 0.0 - dst.z = (src0.z != src1.z) ? 1.0 : 0.0 - dst.w = (src0.w != src1.w) ? 1.0 : 0.0 - - -1.5.22 STR - Set On True - - dst.x = 1.0 - dst.y = 1.0 - dst.z = 1.0 - dst.w = 1.0 - - -1.5.23 TEX - Texture Lookup - - TBD - - -1.5.24 TXD - Texture Lookup with Derivatives - - TBD - - -1.5.25 TXP - Projective Texture Lookup - - TBD - - -1.5.26 UP2H - Unpack Two 16-Bit Floats - - TBD - - -1.5.27 UP2US - Unpack Two Unsigned 16-Bit Scalars - - TBD - - -1.5.28 UP4B - Unpack Four Signed 8-Bit Values - - TBD - - -1.5.29 UP4UB - Unpack Four Unsigned 8-Bit Scalars - - TBD - - -1.5.30 X2D - 2D Coordinate Transformation - - dst.x = src0.x + src1.x * src2.x + src1.y * src2.y - dst.y = src0.y + src1.x * src2.z + src1.y * src2.w - dst.z = src0.x + src1.x * src2.x + src1.y * src2.y - dst.w = src0.y + src1.x * src2.z + src1.y * src2.w - - -1.6 GL_NV_vertex_program2 --------------------------- - - -1.6.1 ARA - Address Register Add - - TBD - - -1.6.2 ARR - Address Register Load With Round - - dst.x = round(src.x) - dst.y = round(src.y) - dst.z = round(src.z) - dst.w = round(src.w) - - -1.6.3 BRA - Branch - - pc = target - - -1.6.4 CAL - Subroutine Call - - push(pc) - pc = target - - -1.6.5 RET - Subroutine Call Return - - pc = pop() - - -1.6.6 SSG - Set Sign - - dst.x = (src.x > 0.0) ? 1.0 : (src.x < 0.0) ? -1.0 : 0.0 - dst.y = (src.y > 0.0) ? 1.0 : (src.y < 0.0) ? -1.0 : 0.0 - dst.z = (src.z > 0.0) ? 1.0 : (src.z < 0.0) ? -1.0 : 0.0 - dst.w = (src.w > 0.0) ? 1.0 : (src.w < 0.0) ? -1.0 : 0.0 - - -1.7 GL_ARB_vertex_program --------------------------- - - -1.7.1 SWZ - Extended Swizzle - - dst.x = src.x - dst.y = src.y - dst.z = src.z - dst.w = src.w - - -1.7.2 XPD - Cross Product - - Alias for CROSSPRODUCT. - - -1.8 GL_ARB_fragment_program ----------------------------- - - -1.8.1 CMP - Compare - - dst.x = (src0.x < 0.0) ? src1.x : src2.x - dst.y = (src0.y < 0.0) ? src1.y : src2.y - dst.z = (src0.z < 0.0) ? src1.z : src2.z - dst.w = (src0.w < 0.0) ? src1.w : src2.w - - -1.8.2 KIL - Conditional Discard - - if (src.x < 0.0 || src.y < 0.0 || src.z < 0.0 || src.w < 0.0) - discard - endif - - -1.8.3 SCS - Sine Cosine - - dst.x = cos(src.x) - dst.y = sin(src.x) - dst.z = 0.0 - dst.y = 1.0 - - -1.8.4 TXB - Texture Lookup With Bias - - TBD - - -1.9 GL_NV_fragment_program2 ----------------------------- - - -1.9.1 NRM - 3-component Vector Normalise - - dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z) - dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z) - dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z) - dst.w = 1.0 - - -1.9.2 DIV - Divide - - dst.x = src0.x / src1.x - dst.y = src0.y / src1.y - dst.z = src0.z / src1.z - dst.w = src0.w / src1.w - - -1.9.3 DP2 - 2-component Dot Product - - dst.x = src0.x * src1.x + src0.y * src1.y - dst.y = src0.x * src1.x + src0.y * src1.y - dst.z = src0.x * src1.x + src0.y * src1.y - dst.w = src0.x * src1.x + src0.y * src1.y - - -1.9.4 DP2A - 2-component Dot Product And Add - - Alias for DOT2ADD. - - -1.9.5 TXL - Texture Lookup With LOD - - TBD - - -1.9.6 BRK - Break - - TBD - - -1.9.7 IF - If - - TBD - - -1.9.10 ELSE - Else - - TBD - - -1.9.11 ENDIF - End If - - TBD - - -1.10 GL_NV_vertex_program3 ---------------------------- - - -1.10.1 PUSHA - Push Address Register On Stack - - push(src.x) - push(src.y) - push(src.z) - push(src.w) - - -1.10.2 POPA - Pop Address Register From Stack - - dst.w = pop() - dst.z = pop() - dst.y = pop() - dst.x = pop() - - -1.11 GL_NV_gpu_program4 ------------------------- - - -1.11.1 CEIL - Ceiling - - dst.x = ceil(src.x) - dst.y = ceil(src.y) - dst.z = ceil(src.z) - dst.w = ceil(src.w) - - -1.11.2 I2F - Integer To Float - - dst.x = (float) src.x - dst.y = (float) src.y - dst.z = (float) src.z - dst.w = (float) src.w - - -1.11.3 NOT - Bitwise Not - - dst.x = ~src.x - dst.y = ~src.y - dst.z = ~src.z - dst.w = ~src.w - - -1.11.4 TRUNC - Truncate - - dst.x = trunc(src.x) - dst.y = trunc(src.y) - dst.z = trunc(src.z) - dst.w = trunc(src.w) - - -1.11.5 SHL - Shift Left - - dst.x = src0.x << src1.x - dst.y = src0.y << src1.x - dst.z = src0.z << src1.x - dst.w = src0.w << src1.x - - -1.11.6 SHR - Shift Right - - dst.x = src0.x >> src1.x - dst.y = src0.y >> src1.x - dst.z = src0.z >> src1.x - dst.w = src0.w >> src1.x - - -1.11.7 AND - Bitwise And - - dst.x = src0.x & src1.x - dst.y = src0.y & src1.y - dst.z = src0.z & src1.z - dst.w = src0.w & src1.w - - -1.11.8 OR - Bitwise Or - - dst.x = src0.x | src1.x - dst.y = src0.y | src1.y - dst.z = src0.z | src1.z - dst.w = src0.w | src1.w - - -1.11.9 MOD - Modulus - - dst.x = src0.x % src1.x - dst.y = src0.y % src1.y - dst.z = src0.z % src1.z - dst.w = src0.w % src1.w - - -1.11.10 XOR - Bitwise Xor - - dst.x = src0.x ^ src1.x - dst.y = src0.y ^ src1.y - dst.z = src0.z ^ src1.z - dst.w = src0.w ^ src1.w - - -1.11.11 SAD - Sum Of Absolute Differences - - dst.x = abs(src0.x - src1.x) + src2.x - dst.y = abs(src0.y - src1.y) + src2.y - dst.z = abs(src0.z - src1.z) + src2.z - dst.w = abs(src0.w - src1.w) + src2.w - - -1.11.12 TXF - Texel Fetch - - TBD - - -1.11.13 TXQ - Texture Size Query - - TBD - - -1.11.14 CONT - Continue - - TBD - - -1.12 GL_NV_geometry_program4 ------------------------------ - - -1.12.1 EMIT - Emit - - TBD - - -1.12.2 ENDPRIM - End Primitive - - TBD - - -1.13 GLSL ----------- - - -1.13.1 BGNLOOP - Begin a Loop - - TBD - - -1.13.2 BGNSUB - Begin Subroutine - - TBD - - -1.13.3 ENDLOOP - End a Loop - - TBD - - -1.13.4 ENDSUB - End Subroutine - - TBD - - -1.13.5 INT - Truncate - - Alias for TRUNC. - - -1.13.6 NOISE1 - 1D Noise - - TBD - - -1.13.7 NOISE2 - 2D Noise - - TBD - - -1.13.8 NOISE3 - 3D Noise - - TBD - - -1.13.9 NOISE4 - 4D Noise - - TBD - - -1.13.10 NOP - No Operation - - Do nothing. - - -1.14 ps_1_1 ------------- - - -1.14.1 TEXKILL - Conditional Discard - - Alias for KIL. - - -1.15 ps_1_4 ------------- - - -1.15.1 TEXLD - Texture Lookup - - Alias for TEX. - - -1.16 ps_2_0 ------------- - - -1.16.1 M4X4 - Multiply Matrix - - Alias for MULTIPLYMATRIX. - - -1.16.2 M4X3 - Multiply Matrix - - Considered for removal from language. - - -1.16.3 M3X4 - Multiply Matrix - - Considered for removal from language. - - -1.16.4 M3X3 - Multiply Matrix - - Considered for removal from language. - - -1.16.5 M3X2 - Multiply Matrix - - Considered for removal from language. - - -1.16.6 CRS - Cross Product - - Alias for XPD. - - -1.16.7 NRM4 - 4-component Vector Normalise - - dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w) - dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w) - dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w) - dst.w = src.w / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w) - - -1.16.8 SINCOS - Sine Cosine - - Alias for SCS. - - -1.16.9 TEXLDB - Texture Lookup With Bias - - Alias for TXB. - - -1.16.10 DP2ADD - 2-component Dot Product And Add - - Alias for DP2A. - - -1.17 ps_2_x ------------- - - -1.17.1 CALL - Subroutine Call - - Alias for CAL. - - -1.17.2 CALLNZ - Subroutine Call If Not Zero - - TBD - - -1.17.3 IFC - If - - TBD - - -1.17.4 BREAK - Break - - Alias for BRK. - - -1.17.5 BREAKC - Break Conditional - - TBD - - -1.17.6 DSX - Derivative Relative To X - - Alias for DDX. - - -1.17.7 DSY - Derivative Relative To Y - - Alias for DDY. - - -1.17.8 TEXLDD - Texture Lookup with Derivatives - - Alias for TXD. - - -1.18 vs_1_1 ------------- - - -1.18.1 EXPP - Approximate Exponential Base 2 - - Use EXP. See also 1.19.3. - - -1.18.2 LOGP - Logarithm Base 2 - - Use LOG. See also 1.19.4. - - -1.19 vs_2_0 ------------- - - -1.19.1 SGN - Set Sign - - Alias for SSG. - - -1.19.2 MOVA - Move Address Register - - Alias for ARR. - - -1.19.3 EXPP - Approximate Exponential Base 2 - - Use EX2. - - -1.19.4 LOGP - Logarithm Base 2 - - Use LG2. - - -2 Explanation of symbols used -============================== - - -2.1 Functions --------------- - - - abs(x) Absolute value of x. - |x| - (x < 0.0) ? -x : x - - ceil(x) Ceiling of x. - - clamp(x,y,z) Clamp x between y and z. - (x < y) ? y : (x > z) ? z : x - - cos(x) Cosine of x. - - floor(x) Floor of x. - - lg2(x) Logarithm base 2 of x. - - max(x,y) Maximum of x and y. - (x > y) ? x : y - - min(x,y) Minimum of x and y. - (x < y) ? x : y - - partialx(x) Derivative of x relative to fragment's X. - - partialy(x) Derivative of x relative to fragment's Y. - - pop() Pop from stack. - - pow(x,y) Raise x to power of y. - - push(x) Push x on stack. - - round(x) Round x. - - sin(x) Sine of x. - - sqrt(x) Square root of x. - - trunc(x) Truncate x. - - -2.2 Keywords -------------- - - - discard Discard fragment. - - dst First destination register. - - dst0 First destination register. - - pc Program counter. - - src First source register. - - src0 First source register. - - src1 Second source register. - - src2 Third source register. - - target Label of target instruction. - - -3 Other tokens -=============== - - -3.1 Declaration Semantic -------------------------- - - - Follows Declaration token if Semantic bit is set. - - Since its purpose is to link a shader with other stages of the pipeline, - it is valid to follow only those Declaration tokens that declare a register - either in INPUT or OUTPUT file. - - SemanticName field contains the semantic name of the register being declared. - There is no default value. - - SemanticIndex is an optional subscript that can be used to distinguish - different register declarations with the same semantic name. The default value - is 0. - - The meanings of the individual semantic names are explained in the following - sections. - - -3.1.1 FACE - - Valid only in a fragment shader INPUT declaration. - - FACE.x is negative when the primitive is back facing. FACE.x is positive - when the primitive is front facing. diff --git a/src/gallium/auxiliary/tgsi/tgsi_scan.c b/src/gallium/auxiliary/tgsi/tgsi_scan.c index e0c5d3d3d6..ced9c94f46 100644 --- a/src/gallium/auxiliary/tgsi/tgsi_scan.c +++ b/src/gallium/auxiliary/tgsi/tgsi_scan.c @@ -36,6 +36,7 @@ #include "util/u_math.h" #include "tgsi/tgsi_parse.h" +#include "tgsi/tgsi_util.h" #include "tgsi/tgsi_scan.h" @@ -84,25 +85,28 @@ tgsi_scan_shader(const struct tgsi_token *tokens, { const struct tgsi_full_instruction *fullinst = &parse.FullToken.FullInstruction; + uint i; assert(fullinst->Instruction.Opcode < TGSI_OPCODE_LAST); info->opcode_count[fullinst->Instruction.Opcode]++; - /* check if we read the frag shader FOG or FACE inputs */ - if (procType == TGSI_PROCESSOR_FRAGMENT) { - uint i; - for (i = 0; i < fullinst->Instruction.NumSrcRegs; i++) { - const struct tgsi_full_src_register *src = - &fullinst->Src[i]; - if (src->Register.File == TGSI_FILE_INPUT || - src->Register.File == TGSI_FILE_SYSTEM_VALUE) { - const int ind = src->Register.Index; - if (info->input_semantic_name[ind] == TGSI_SEMANTIC_FOG) { - info->uses_fogcoord = TRUE; - } - else if (info->input_semantic_name[ind] == TGSI_SEMANTIC_FACE) { - info->uses_frontfacing = TRUE; + for (i = 0; i < fullinst->Instruction.NumSrcRegs; i++) { + const struct tgsi_full_src_register *src = + &fullinst->Src[i]; + int ind = src->Register.Index; + + /* Mark which inputs are effectively used */ + if (src->Register.File == TGSI_FILE_INPUT) { + unsigned usage_mask; + usage_mask = tgsi_util_get_inst_usage_mask(fullinst, i); + if (src->Register.Indirect) { + for (ind = 0; ind < info->num_inputs; ++ind) { + info->input_usage_mask[ind] |= usage_mask; } + } else { + assert(ind >= 0); + assert(ind < PIPE_MAX_SHADER_INPUTS); + info->input_usage_mask[ind] |= usage_mask; } } } diff --git a/src/gallium/auxiliary/tgsi/tgsi_scan.h b/src/gallium/auxiliary/tgsi/tgsi_scan.h index 27de33f799..e75280336f 100644 --- a/src/gallium/auxiliary/tgsi/tgsi_scan.h +++ b/src/gallium/auxiliary/tgsi/tgsi_scan.h @@ -45,6 +45,7 @@ struct tgsi_shader_info ubyte input_semantic_name[PIPE_MAX_SHADER_INPUTS]; /**< TGSI_SEMANTIC_x */ ubyte input_semantic_index[PIPE_MAX_SHADER_INPUTS]; ubyte input_interpolate[PIPE_MAX_SHADER_INPUTS]; + ubyte input_usage_mask[PIPE_MAX_SHADER_INPUTS]; ubyte input_cylindrical_wrap[PIPE_MAX_SHADER_INPUTS]; ubyte output_semantic_name[PIPE_MAX_SHADER_OUTPUTS]; /**< TGSI_SEMANTIC_x */ ubyte output_semantic_index[PIPE_MAX_SHADER_OUTPUTS]; @@ -61,8 +62,6 @@ struct tgsi_shader_info boolean writes_z; /**< does fragment shader write Z value? */ boolean writes_edgeflag; /**< vertex shader outputs edgeflag */ boolean uses_kill; /**< KIL or KILP instruction used? */ - boolean uses_fogcoord; /**< fragment shader uses fog coord? */ - boolean uses_frontfacing; /**< fragment shader uses front/back-face flag? */ struct { unsigned name; diff --git a/src/gallium/auxiliary/tgsi/tgsi_sse2.c b/src/gallium/auxiliary/tgsi/tgsi_sse2.c index d5061f8b51..785a9fb035 100644 --- a/src/gallium/auxiliary/tgsi/tgsi_sse2.c +++ b/src/gallium/auxiliary/tgsi/tgsi_sse2.c @@ -1244,16 +1244,9 @@ emit_sub( make_xmm( xmm_src ) ); } - - - - - - /** * Register fetch. */ - static void emit_fetch( struct x86_function *func, @@ -1338,7 +1331,6 @@ emit_fetch( /** * Register store. */ - static void emit_store( struct x86_function *func, @@ -1455,7 +1447,6 @@ fetch_texel( struct tgsi_sampler **sampler, /** * High-level instruction translators. */ - static void emit_tex( struct x86_function *func, const struct tgsi_full_instruction *inst, @@ -1507,7 +1498,6 @@ emit_tex( struct x86_function *func, get_temp( TEMP_R0, 3 ), make_xmm( 3 ) ); - if (projected) { FETCH( func, *inst, 3, 0, 3 ); @@ -1535,7 +1525,6 @@ emit_tex( struct x86_function *func, args[0] = get_temp( TEMP_R0, 0 ); args[1] = get_sampler_ptr( unit ); - emit_func_call( func, 0, args, @@ -1569,7 +1558,8 @@ emit_kil( /* This mask stores component bits that were already tested. Note that * we test if the value is less than zero, so 1.0 and 0.0 need not to be - * tested. */ + * tested. + */ uniquemask = 0; FOR_EACH_CHANNEL( chan_index ) { @@ -1715,22 +1705,26 @@ emit_cmp( /** - * Check if inst src/dest regs use indirect addressing into temporary - * register file. + * Check if inst src/dest regs use indirect addressing into temporary, + * input or output register files. */ static boolean -indirect_temp_reference(const struct tgsi_full_instruction *inst) +indirect_reg_reference(const struct tgsi_full_instruction *inst) { uint i; for (i = 0; i < inst->Instruction.NumSrcRegs; i++) { const struct tgsi_full_src_register *reg = &inst->Src[i]; - if (reg->Register.File == TGSI_FILE_TEMPORARY && + if ((reg->Register.File == TGSI_FILE_TEMPORARY || + reg->Register.File == TGSI_FILE_INPUT || + reg->Register.File == TGSI_FILE_OUTPUT) && reg->Register.Indirect) return TRUE; } for (i = 0; i < inst->Instruction.NumDstRegs; i++) { const struct tgsi_full_dst_register *reg = &inst->Dst[i]; - if (reg->Register.File == TGSI_FILE_TEMPORARY && + if ((reg->Register.File == TGSI_FILE_TEMPORARY || + reg->Register.File == TGSI_FILE_INPUT || + reg->Register.File == TGSI_FILE_OUTPUT) && reg->Register.Indirect) return TRUE; } @@ -1746,7 +1740,7 @@ emit_instruction( unsigned chan_index; /* we can't handle indirect addressing into temp register file yet */ - if (indirect_temp_reference(inst)) + if (indirect_reg_reference(inst)) return FALSE; switch (inst->Instruction.Opcode) { @@ -2931,7 +2925,6 @@ tgsi_emit_sse2( x86_make_disp( get_machine_base(), Offset( struct tgsi_exec_machine, Samplers ) ) ); - while( !tgsi_parse_end_of_tokens( &parse ) && ok ) { tgsi_parse_token( &parse ); @@ -3015,4 +3008,3 @@ tgsi_emit_sse2( } #endif /* PIPE_ARCH_X86 */ - diff --git a/src/gallium/auxiliary/tgsi/tgsi_util.c b/src/gallium/auxiliary/tgsi/tgsi_util.c index 0a7e4105a8..3ec5496416 100644 --- a/src/gallium/auxiliary/tgsi/tgsi_util.c +++ b/src/gallium/auxiliary/tgsi/tgsi_util.c @@ -163,3 +163,149 @@ tgsi_util_set_full_src_register_sign_mode( assert( 0 ); } } + +/** + * Determine which channels of the specificed src register are effectively + * used by this instruction. + */ +unsigned +tgsi_util_get_inst_usage_mask(const struct tgsi_full_instruction *inst, + unsigned src_idx) +{ + const struct tgsi_full_src_register *src = &inst->Src[src_idx]; + unsigned write_mask = inst->Dst[0].Register.WriteMask; + unsigned read_mask; + unsigned usage_mask; + unsigned chan; + + switch (inst->Instruction.Opcode) { + case TGSI_OPCODE_MOV: + case TGSI_OPCODE_ARL: + case TGSI_OPCODE_ARR: + case TGSI_OPCODE_RCP: + case TGSI_OPCODE_MUL: + case TGSI_OPCODE_DIV: + case TGSI_OPCODE_ADD: + case TGSI_OPCODE_MIN: + case TGSI_OPCODE_MAX: + case TGSI_OPCODE_SLT: + case TGSI_OPCODE_SGE: + case TGSI_OPCODE_MAD: + case TGSI_OPCODE_SUB: + case TGSI_OPCODE_LRP: + case TGSI_OPCODE_CND: + case TGSI_OPCODE_FRC: + case TGSI_OPCODE_CEIL: + case TGSI_OPCODE_CLAMP: + case TGSI_OPCODE_FLR: + case TGSI_OPCODE_ROUND: + case TGSI_OPCODE_POW: + case TGSI_OPCODE_ABS: + case TGSI_OPCODE_COS: + case TGSI_OPCODE_SIN: + case TGSI_OPCODE_DDX: + case TGSI_OPCODE_DDY: + case TGSI_OPCODE_SEQ: + case TGSI_OPCODE_SGT: + case TGSI_OPCODE_SLE: + case TGSI_OPCODE_SNE: + case TGSI_OPCODE_SSG: + case TGSI_OPCODE_CMP: + case TGSI_OPCODE_TRUNC: + case TGSI_OPCODE_NOT: + case TGSI_OPCODE_AND: + case TGSI_OPCODE_OR: + case TGSI_OPCODE_XOR: + case TGSI_OPCODE_SAD: + /* Channel-wise operations */ + read_mask = write_mask; + break; + + case TGSI_OPCODE_EX2: + case TGSI_OPCODE_LG2: + case TGSI_OPCODE_RCC: + read_mask = TGSI_WRITEMASK_X; + break; + + case TGSI_OPCODE_SCS: + read_mask = write_mask & TGSI_WRITEMASK_XY ? TGSI_WRITEMASK_X : 0; + break; + + case TGSI_OPCODE_EXP: + case TGSI_OPCODE_LOG: + read_mask = write_mask & TGSI_WRITEMASK_XYZ ? TGSI_WRITEMASK_X : 0; + break; + + case TGSI_OPCODE_DP2A: + read_mask = src_idx == 2 ? TGSI_WRITEMASK_X : TGSI_WRITEMASK_XY; + break; + + case TGSI_OPCODE_DP2: + read_mask = TGSI_WRITEMASK_XY; + break; + + case TGSI_OPCODE_DP3: + read_mask = TGSI_WRITEMASK_XYZ; + break; + + case TGSI_OPCODE_DP4: + read_mask = TGSI_WRITEMASK_XYZW; + break; + + case TGSI_OPCODE_DPH: + read_mask = src_idx == 0 ? TGSI_WRITEMASK_XYZ : TGSI_WRITEMASK_XYZW; + break; + + case TGSI_OPCODE_TEX: + case TGSI_OPCODE_TXD: + case TGSI_OPCODE_TXB: + case TGSI_OPCODE_TXL: + case TGSI_OPCODE_TXP: + if (src_idx == 0) { + switch (inst->Texture.Texture) { + case TGSI_TEXTURE_1D: + case TGSI_TEXTURE_SHADOW1D: + read_mask = TGSI_WRITEMASK_X; + break; + + case TGSI_TEXTURE_2D: + case TGSI_TEXTURE_RECT: + case TGSI_TEXTURE_SHADOW2D: + case TGSI_TEXTURE_SHADOWRECT: + read_mask = TGSI_WRITEMASK_XY; + break; + + case TGSI_TEXTURE_3D: + case TGSI_TEXTURE_CUBE: + read_mask = TGSI_WRITEMASK_XYZ; + break; + + default: + assert(0); + read_mask = 0; + } + + if (inst->Instruction.Opcode != TGSI_OPCODE_TEX) { + read_mask |= TGSI_WRITEMASK_W; + } + } else { + /* A safe approximation */ + read_mask = TGSI_WRITEMASK_XYZW; + } + break; + + default: + /* Assume all channels are read */ + read_mask = TGSI_WRITEMASK_XYZW; + break; + } + + usage_mask = 0; + for (chan = 0; chan < 4; ++chan) { + if (read_mask & (1 << chan)) { + usage_mask |= 1 << tgsi_util_get_full_src_register_swizzle(src, chan); + } + } + + return usage_mask; +} diff --git a/src/gallium/auxiliary/tgsi/tgsi_util.h b/src/gallium/auxiliary/tgsi/tgsi_util.h index 19ee2e7cf2..04702ba982 100644 --- a/src/gallium/auxiliary/tgsi/tgsi_util.h +++ b/src/gallium/auxiliary/tgsi/tgsi_util.h @@ -34,6 +34,7 @@ extern "C" { struct tgsi_src_register; struct tgsi_full_src_register; +struct tgsi_full_instruction; void * tgsi_align_128bit( @@ -71,6 +72,10 @@ tgsi_util_set_full_src_register_sign_mode( struct tgsi_full_src_register *reg, unsigned sign_mode ); +unsigned +tgsi_util_get_inst_usage_mask(const struct tgsi_full_instruction *inst, + unsigned src_idx); + #if defined __cplusplus } #endif |